icml.bib

@article{thompson1933likelihood,
  title={On the likelihood that one unknown probability exceeds another in view of the evidence of two samples},
  author={Thompson, William R},
  journal={Biometrika},
  volume={25},
  number={3/4},
  pages={285--294},
  year={1933},
  publisher={JSTOR}
}
@article{bush1953stochastic,
  title={A stochastic model with applications to learning},
  author={Bush, Robert R and Mosteller, Frederick},
  journal={The Annals of Mathematical Statistics},
  pages={559--585},
  year={1953},
  publisher={JSTOR}
}

@article{grace2017will,
  title={When will AI exceed human performance? Evidence from AI experts},
  author={Grace, Katja and Salvatier, John and Dafoe, Allan and Zhang, Baobao and Evans, Owain},
  journal={arXiv preprint arXiv:1705.08807},
  year={2017}
}
@inproceedings{brown2017libratus,
  title={Libratus: the superhuman AI for no-limit poker},
  author={Brown, Noam and Sandholm, Tuomas},
  booktitle={Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence},
  year={2017}
}
@article{moravvcik2017deepstack,
  title={Deepstack: Expert-level artificial intelligence in heads-up no-limit poker},
  author={Morav{\v{c}}{\'\i}k, Matej and Schmid, Martin and Burch, Neil and Lis{\`y}, Viliam and Morrill, Dustin and Bard, Nolan and Davis, Trevor and Waugh, Kevin and Johanson, Michael and Bowling, Michael},
  journal={Science},
  volume={356},
  number={6337},
  pages={508--513},
  year={2017},
  publisher={American Association for the Advancement of Science}
}
@article{silver2016mastering,
  title={Mastering the game of Go with deep neural networks and tree search},
  author={Silver, David and Huang, Aja and Maddison, Chris J and Guez, Arthur and Sifre, Laurent and Van Den Driessche, George and Schrittwieser, Julian and Antonoglou, Ioannis and Panneershelvam, Veda and Lanctot, Marc and others},
  journal={nature},
  volume={529},
  number={7587},
  pages={484--489},
  year={2016},
  publisher={Nature Research}
}
@article{drucker1976pension,
  title={Pension fund socialism},
  author={Drucker, Peter F},
  journal={The Public Interest},
  number={42},
  pages={3},
  year={1976},
  publisher={National Affairs, inc.}
}
@article{campbell2002deep,
  title={Deep blue},
  author={Campbell, Murray and Hoane Jr, A Joseph and Hsu, Feng-hsiung},
  journal={Artificial intelligence},
  volume={134},
  number={1-2},
  pages={57--83},
  year={2002},
  publisher={Elsevier}
}
@article{silver2017mastering,
  title={Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm},
  author={Silver, David and Hubert, Thomas and Schrittwieser, Julian and Antonoglou, Ioannis and Lai, Matthew and Guez, Arthur and Lanctot, Marc and Sifre, Laurent and Kumaran, Dharshan and Graepel, Thore and others},
  journal={arXiv preprint arXiv:1712.01815},
  year={2017}
}
@article{rahwan2016moral,
  title={Moral Machine},
  author={Rahwan, Iyad and Bonnefon, Jean-Francois and Shariff, Azim and others},
  journal={Scalable Cooperation, MIT Media Lab. At: http://moralmachine. mit. edu (accessed 21 August 2016)},
  year={2016}
}
@article{kim2018computational,
  title={A Computational Model of Commonsense Moral Decision Making},
  author={Kim, Richard and Kleiman-Weiner, Max and Abeliuk, Andres and Awad, Edmond and Dsouza, Sohan and Tenenbaum, Josh and Rahwan, Iyad},
  journal={arXiv preprint arXiv:1801.04346},
  year={2018}
}
@article{lerer2017maintaining,
  title={Maintaining cooperation in complex social dilemmas using deep reinforcement learning},
  author={Lerer, Adam and Peysakhovich, Alexander},
  journal={arXiv preprint arXiv:1707.01068},
  year={2017}
}
@article{cheng2015global,
  title={Global contrast based salient region detection},
  author={Cheng, Ming-Ming and Mitra, Niloy J and Huang, Xiaolei and Torr, Philip HS and Hu, Shi-Min},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume={37},
  number={3},
  pages={569--582},
  year={2015},
  publisher={IEEE}
}
@article{rittel1973dilemmas,
  title={Dilemmas in a general theory of planning},
  author={Rittel, Horst WJ and Webber, Melvin M},
  journal={Policy sciences},
  volume={4},
  number={2},
  pages={155--169},
  year={1973},
  publisher={Springer}
}
@article{head2008wicked,
  title={Wicked problems in public policy},
  author={Head, Brian W and others},
  journal={Public policy},
  volume={3},
  number={2},
  pages={101},
  year={2008},
  publisher={John Curtin Institute of Public Policy, Curtin University of Technology}
}
@article{camillus2008strategy,
  title={Strategy as a wicked problem},
  author={Camillus, John C},
  journal={Harvard business review},
  volume={86},
  number={5},
  pages={98},
  year={2008}
}
@inproceedings{levin2007playing,
  title={Playing it forward: Path dependency, progressive incrementalism, and the ‘Super Wicked’problem of global climate change},
  author={Levin, Kelly and Cashore, Benjamin and Bernstein, Steven and Auld, Graeme},
  booktitle={International Studies Association 48th Annual Convention. Chicago, February},
  year={2007},
  organization={Citeseer}
}
@book{pearl2009causality,
  title={Causality},
  author={Pearl, Judea},
  year={2009},
  publisher={Cambridge university press}
}
@article{mcdermott1976artificial,
  title={Artificial intelligence meets natural stupidity},
  author={McDermott, Drew},
  journal={ACM SIGART Bulletin},
  number={57},
  pages={4--9},
  year={1976},
  publisher={ACM}
}
@article{lombrozo2006structure,
  title={The structure and function of explanations},
  author={Lombrozo, Tania},
  journal={Trends in cognitive sciences},
  volume={10},
  number={10},
  pages={464--470},
  year={2006},
  publisher={Elsevier}
}
@article{grosz1996collaborative,
  title={Collaborative Systems (AAAI-94 Presidential Address)},
  author={Grosz, Barbara J},
  journal={AI magazine},
  volume={17},
  number={2},
  pages={67},
  year={1996}
}
@inproceedings{ciardo2002using,
  title={Using edge-valued decision diagrams for symbolic generation of shortest paths},
  author={Ciardo, Gianfranco and Siminiceanu, Radu},
  booktitle={International Conference on Formal Methods in Computer-Aided Design},
  pages={256--273},
  year={2002},
  organization={Springer}
}
@inproceedings{ng1999policy,
  title={Policy invariance under reward transformations: Theory and application to reward shaping},
  author={Ng, Andrew Y and Harada, Daishi and Russell, Stuart},
  booktitle={ICML},
  volume={99},
  pages={278--287},
  year={1999}
}
@article{de2017multi,
  title={Multi-step reinforcement learning: A unifying algorithm},
  author={De Asis, Kristopher and Hernandez-Garcia, J Fernando and Holland, G Zacharias and Sutton, Richard S},
  journal={arXiv preprint arXiv:1703.01327},
  year={2017}
}
@article{henriques2015high,
  title={High-speed tracking with kernelized correlation filters},
  author={Henriques, Jo{\~a}o F and Caseiro, Rui and Martins, Pedro and Batista, Jorge},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume={37},
  number={3},
  pages={583--596},
  year={2015},
  publisher={IEEE}
}
@article{sutton1999between,
  title={Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning},
  author={Sutton, Richard S and Precup, Doina and Singh, Satinder},
  journal={Artificial intelligence},
  volume={112},
  number={1-2},
  pages={181--211},
  year={1999},
  publisher={Elsevier}
}
@inproceedings{bacon2017option,
  title={The Option-Critic Architecture.},
  author={Bacon, Pierre-Luc and Harb, Jean and Precup, Doina},
  booktitle={AAAI},
  pages={1726--1734},
  year={2017}
}
@article{simon1972theories,
  title={Theories of bounded rationality},
  author={Simon, Herbert A},
  journal={Decision and organization},
  volume={1},
  number={1},
  pages={161--176},
  year={1972}
}
@inproceedings{huang2015supporting,
  title={Supporting mental model accuracy in trigger-action programming},
  author={Huang, Justin and Cakmak, Maya},
  booktitle={Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing},
  pages={215--225},
  year={2015},
  organization={ACM}
}
@inproceedings{subramanian2011learning,
  title={Learning options through human interaction},
  author={Subramanian, Kaushik and Isbell, Charles and Thomaz, Andrea},
  booktitle={2011 IJCAI Workshop on Agents Learning Interactively from Human Teachers (ALIHT)},
  year={2011},
  organization={Citeseer}
}
@article{knox2015framing,
  title={Framing reinforcement learning from human reward: Reward positivity, temporal discounting, episodicity, and performance},
  author={Knox, W Bradley and Stone, Peter},
  journal={Artificial Intelligence},
  volume={225},
  pages={24--50},
  year={2015},
  publisher={Elsevier}
}
@inproceedings{isbell2001social,
  title={A social reinforcement learning agent},
  author={Isbell, Charles and Shelton, Christian R and Kearns, Michael and Singh, Satinder and Stone, Peter},
  booktitle={Proceedings of the fifth international conference on Autonomous agents},
  pages={377--384},
  year={2001},
  organization={ACM}
}
@inproceedings{loftin2014strategy,
  title={A Strategy-Aware Technique for Learning Behaviors from Discrete Human Feedback.},
  author={Loftin, Robert Tyler and MacGlashan, James and Peng, Bei and Taylor, Matthew E and Littman, Michael L and Huang, Jeff and Roberts, David L},
  booktitle={AAAI},
  pages={937--943},
  year={2014}
}
@inproceedings{taylor2007transfer,
  title={Transfer via inter-task mappings in policy search reinforcement learning},
  author={Taylor, Matthew E and Whiteson, Shimon and Stone, Peter},
  booktitle={Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems},
  pages={37},
  year={2007},
  organization={ACM}
}
@article{wang2017erm,
  title={On the ERM Principle with Networked Data},
  author={Wang, Yuanhong and Wang, Yuyi and Liu, Xingwu and Pu, Juhua},
  journal={arXiv preprint arXiv:1711.04297},
  year={2017}
}
@inproceedings{abraham2010highway,
  title={Highway dimension, shortest paths, and provably efficient algorithms},
  author={Abraham, Ittai and Fiat, Amos and Goldberg, Andrew V and Werneck, Renato F},
  booktitle={Proceedings of the twenty-first annual ACM-SIAM symposium on Discrete Algorithms},
  pages={782--793},
  year={2010},
  organization={Society for Industrial and Applied Mathematics}
}
@inproceedings{funke2011path,
  title={Path shapes: an alternative method for map matching and fully autonomous self-localization},
  author={Funke, Stefan and Storandt, Sabine},
  booktitle={Proceedings of the 19th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems},
  pages={319--328},
  year={2011},
  organization={ACM}
}
@inproceedings{bast2007transit,
  title={In transit to constant time shortest-path queries in road networks},
  author={Bast, Holger and Funke, Stefan and Matijevic, Domagoj and Sanders, Peter and Schultes, Dominik},
  booktitle={Proceedings of the Meeting on Algorithm Engineering \& Expermiments},
  pages={46--59},
  year={2007},
  organization={Society for Industrial and Applied Mathematics}
}
@inproceedings{ramirez2010probabilistic,
  title={Probabilistic plan recognition using off-the-shelf classical planners},
  author={Ram{\i}rez, Miquel and Geffner, Hector},
  booktitle={Proceedings of the Conference of the Association for the Advancement of Artificial Intelligence (AAAI 2010)},
  pages={1121--1126},
  year={2010}
}
@article{kaye2000minesweeper,
  title={Minesweeper is NP-complete},
  author={Kaye, Richard},
  journal={The Mathematical Intelligencer},
  volume={22},
  number={2},
  pages={9--15},
  year={2000},
  publisher={Springer}
}
@inproceedings{newson2009hidden,
  title={Hidden Markov map matching through noise and sparseness},
  author={Newson, Paul and Krumm, John},
  booktitle={Proceedings of the 17th ACM SIGSPATIAL international conference on advances in geographic information systems},
  pages={336--343},
  year={2009},
  organization={ACM}
}
@inproceedings{cheng2011taxisim,
  title={Taxisim: A multiagent simulation platform for evaluating taxi fleet operations},
  author={Cheng, Shih-Fen and Nguyen, Thi Duong},
  booktitle={Web Intelligence and Intelligent Agent Technology (WI-IAT), 2011 IEEE/WIC/ACM International Conference on},
  volume={2},
  pages={14--21},
  year={2011},
  organization={IEEE}
}
@article{foerster2017counterfactual,
  title={Counterfactual multi-agent policy gradients},
  author={Foerster, Jakob and Farquhar, Gregory and Afouras, Triantafyllos and Nardelli, Nantas and Whiteson, Shimon},
  journal={arXiv preprint arXiv:1705.08926},
  year={2017}
}
@inproceedings{freedman2018adapting,
  title={Adapting a kidney exchange algorithm to align with human values},
  author={Freedman, Rachel and Borg, Jana Schaich and Sinnott-Armstrong, Walter and Dickerson, John P and Conitzer, Vincent},
  booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{marom2018belief,
  title={Belief Reward Shaping in Reinforcement Learning},
  author={Marom, Ofir and Rosman, Benjamin},
  booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{ribeiro2018anchors,
  title={Anchors: High-Precision Model-Agnostic Explanations},
  author={Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin},
  booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{li2018file,
  title={FILE: A Novel Framework for Predicting Social Status in Signed Networks},
  author={Xiaoming Li, Hui Fang, Jie Zhang},
  booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{freedman2018adapting,
  title={Adapting a kidney exchange algorithm to align with human values},
  author={Freedman, Rachel and Borg, Jana Schaich and Sinnott-Armstrong, Walter and Dickerson, John P and Conitzer, Vincent},
  booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{kahng2018ranking,
  title={Ranking wily people who rank each other},
  author={Kahng, Anson and Kotturi, Yasmine and Kulkarni, Chinmay and Kurokawa, David and Procaccia, Ariel D},
   booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018},
}
@inproceedings{fulton2018safe,
  title={Safe Reinforcement Learning via Formal Methods},
  author={Fulton, Nathan and Platzer, Andr{\'e}},
  year={2018},
   booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
}
@inproceedings{hessel2018rainbow,
  title={Rainbow: Combining Improvements in Deep Reinforcement Learning},
  author={Hessel, Matteo and Modayil, Joseph and Van Hasselt, Hado and Schaul, Tom and Ostrovski, Georg and Dabney, Will and Horgan, Dan and Piot, Bilal and Azar, Mohammad and Silver, David},
   booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{foerster2018counterfactual,
  title={Counterfactual multi-agent policy gradients},
  author={Foerster, Jakob and Farquhar, Gregory and Afouras, Triantafyllos and Nardelli, Nantas and Whiteson, Shimon},
   booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{gaspers18,
    title={Minesweeper with Limited Moves},
    author={Serge Gaspers, Stefan Rümmele, Abdallah Saffidine, Kevin Tran},
   booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{sohrabi2018ai,
  title={An AI Planning Solution to Scenario Generation for Enterprise Risk Management},
  author={Sohrabi, Shirin and Riabov, Anton V and Katz, Michael and Udrea, Octavian},
   booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{asai2018classical,
  title={Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary},
  author={Asai, Masataro and Fukunaga, Alex},
   booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{song18risk,
    title={Risk-aware Proactive Scheduling via Conditional Value-at-Risk},
    author={Wen Song, Donghun Kang, Jie Zhang, Hui Xi},
   booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{blum2018sublin,
    title={Sublinear Search Spaces for Shortest Path Planning in Grid and Road Networks},
    author={Johannes Blum, Stefan Funke, Sabine Storandt},
   booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{blum2018algorithms,
  title={Algorithms for Generalized Topic Modeling},
  author={Blum, Avrim and Haghtalab, Nika},
   booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{ashtiani2018sample,
  title={Sample-Efficient Learning of Mixtures},
  author={Ashtiani, Hassan and Ben-David, Shai and Mehrabian, Abbas},
  booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{nguyen2018provable,
  title={A Provable Approach for Double-Sparse Coding},
  author={Nguyen, Thanh and Wong, Raymond KW and Hegde, Chinmay},
  booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{wang2018erm,
  title={On the ERM Principle with Networked Data},
  author={Wang, Yuanhong and Wang, Yuyi and Liu, Xingwu and Pu, Juhua},
  booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{harb2018waiting,
  title={When waiting is not an option: Learning options with a deliberation cost},
  author={Harb, Jean and Bacon, Pierre-Luc and Klissarov, Martin and Precup, Doina},
  booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{li2018optimal,
  title={An Optimal Online Method of Selecting Source Policies for Reinforcement Learning},
  author={Li, Siyuan and Zhang, Chongjie},
  booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{de2018multi,
  title={Multi-step reinforcement learning: A unifying algorithm},
  author={De Asis, Kristopher and Hernandez-Garcia, J Fernando and Holland, G Zacharias and Sutton, Richard S},
  booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{tavakoli2018action,
  title={Action Branching Architectures for Deep Reinforcement Learning},
  author={Tavakoli, Arash and Pardo, Fabio and Kormushev, Petar},
  booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{sharma2018phase,
  title={Phase-Parametric Policies for Reinforcement Learning in Cyclic Environments},
  author={Sharma, Arjun and Kitani, Kris M},
  booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{xinrun2018catching,
  title={Catching Captain Jack: Efficient Time and Space Dependent Patrols to Combat Oil-Siphoning in International Waters},
  author={Xinrun Wang, Bo An and Strobel, Martin and Kong, Fookwai},
    booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{tang2018multi,
  title={Multi-Entity Dependence Learning with Rich Context via Conditional Variational Auto-encoder},
  author={Tang, Luming and Xue, Yexiang and Chen, Di and Gomes, Carla P},
  booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{yang18poiss,
    title={A Poisson Gamma Probabilistic Model for Latent Node-group Memberships in Dynamic Networks},
    author={Sikun Yang, Heinz Koeppl},
  booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{wang2018kernel,
  title={Kernel Cross-Correlator},
  author={Wang, Chen and Zhang, Le and Xie, Lihua and Yuan, Junsong},
    booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{sharon2018traffic,
  title={Traffic Optimization For a Mixture of Self-interested and Compliant Agents},
  author={Sharon, Guni and Albert, Michael and Rambha, Tarun and Boyles, Stephen and Stone, Peter},
    booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{kumar2018load,
  title={Load Scheduling of Simple Temporal Networks Under Dynamic Resource Pricing},
  author={Kumar, TK Satish and Wang, Zhi and Craig, Anoop Kumar Craig Milo Rogers and Knoblock, A},
    booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{liu2017change,
  title={A Change-Detection based Framework for Piecewise-stationary Multi-Armed Bandit Problem},
  author={Liu, Fang and Lee, Joohyun and Shroff, Ness},
  booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{benavent2018experimental,
  title={An Experimental Study of Advice in Sequential Decision-Making under Uncertainty},
  author={Benavent, Florian and Zanuttini, Bruno},
  booktitle={32nd AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{paul2018alternating,
  title={Alternating Optimisation and Quadrature for Robust Control},
  author={Paul, Supratik and Chatzilygeroudis, Konstantinos and Ciosek, Kamil and Mouret, Jean-Baptiste and Osborne, Michael and Whiteson, Shimon and Ivaldi, Serena and Ugurlu, Barkan},
  booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{jiang2018pac,
  title={PAC Reinforcement Learning with an Imperfect Model},
  author={Jiang, Nan},
    booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{harutyunyan2018learning,
  title={Learning with options that terminate off-policy},
  author={Harutyunyan, Anna and Vrancx, Peter and Bacon, Pierre-Luc and Precup, Doina and Nowe, Ann},
  booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{brown18irl,
    title={Efficient Probabilistic Performance Bounds for Inverse Reinforcement Learning},
    author={Daniel Brown, Scott Niekum},
  booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{mattmueller18,
    title={On the Relationship Between State-Dependent Action Costs and Conditional Effects in Planning},
    author={Robert Mattmueller, Florian Geißer, Benedict Wright, Bernhard Nebel},
  booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@inproceedings{hooker18toward,
    title={Toward Non-Intuition-Based Machine Ethics},
    author={John Hooker and Tae Wan Kim},
  booktitle={Proceedings of the First AAAI/ACM Conference on Artificial Intelligence, Ethics & Society},
  year={2018}
}
@inproceedings{larosa18trust,
    title={Impacts on Trust of Healthcare AI},
    author={Emily Larosa and David Danks},
  booktitle={Proceedings of the First AAAI/ACM Conference on Artificial Intelligence, Ethics & Society},
  year={2018}
}
@inproceedings{erdelyi18,
  title={Regulating Artificial Intelligence Proposal for a Global Solution},
  author={Olivia J. Erdelyi, Judy Goldsmith.},
  booktitle={Proceedings of the First AAAI/ACM Conference on Artificial Intelligence, Ethics & Society},
  year={2018}
}
@inproceedings{scheessele18frame,
    title={A framework for grounding the moral status of intelligent machines},
    author={Michael Scheessele},
  booktitle={Proceedings of the First AAAI/ACM Conference on Artificial Intelligence, Ethics & Society},
  year={2018}
}
@inproceedings{estrada18val,
    title={Value Alignment, Fair Play, and the Rights of Service Robots},
    author={Daniel Estrada},
  booktitle={Proceedings of the First AAAI/ACM Conference on Artificial Intelligence, Ethics & Society},
  year={2018}
}
@inproceedings{kramer18when,
    title={When Do People Want AI to Make Decisions?},
    author={Max Kramer, Jana Schaich Borg, Vincent Conitzer and Walter Sinnott-Armstrong},
  booktitle={Proceedings of the First AAAI/ACM Conference on Artificial Intelligence, Ethics & Society},
  year={2018}
}
@inproceedings{gruze18wicked,
    title={Rethinking AI Strategy and Policy as Entangled Super Wicked Problems},
    author={Ross Gruetzemacher},
  booktitle={Proceedings of the First AAAI/ACM Conference on Artificial Intelligence, Ethics & Society},
  year={2018}
}
@inproceedings{london18reg,
    title={Regulating Autonomous Vehicles: A Policy Proposal},
    author={Alex John London and David Danks},
  booktitle={Proceedings of the First AAAI/ACM Conference on Artificial Intelligence, Ethics & Society},
  year={2018}
}
@inproceedings{iyer18explan,
    title={Transparency and Explanation in Deep Reinforcement Learning Neural Networks},
    author={Rahul Iyer, Yuezhang Li, Huao Li, Michael Lewis, Ramitha Sundar and Katia Sycara}
  booktitle={Proceedings of the First AAAI/ACM Conference on Artificial Intelligence, Ethics & Society},
  year={2018}
}
    
@inproceedings{sun18shape,
    title={Designing Non-greedy Reinforcement Learning Agents with Diminishing Reward Shaping},
    author={Fan-Yun Sun, Yen-Yu Chang, Yueh-Hua Wu and Shou-De Lin},
  booktitle={Proceedings of the First AAAI/ACM Conference on Artificial Intelligence, Ethics & Society},
  year={2018}
}
@inproceedings{kim18comp,
    title={A Computational Model of Commonsense Moral Decision Making},
    author={Richard Kim, Max Kleiman-Weiner, Andres Abeliuk, Edmond Awad, Sohan Dsouza, Josh Tenenbaum and Iyad Rahwan},
  booktitle={Proceedings of the First AAAI/ACM Conference on Artificial Intelligence, Ethics & Society},
  year={2018}
}
@inproceedings{vanderelst18,
    title={The Dark Side of Ethical Robots},
    author={Dieter Vanderelst and Alan Winfield},
  booktitle={Proceedings of the First AAAI/ACM Conference on Artificial Intelligence, Ethics & Society},
  year={2018}
}    
@inproceedings{henderson18ethics,
    title={Ethical Challenges in Data-Driven Dialogue Systems},
    author={Peter Henderson, Koustuv Sinha, Nicolas Angelard-Gontier, Nan Rosemary Ke, Genevieve Fried, Ryan Lowe, Joelle Pineau},
    booktitle={Proceedings of the First AAAI/ACM Conference on Artificial Intelligence, Ethics & Society},
    year={2018}
}    
@inproceedings{eicher18watson,
    title={Jill Watson Doesn’t Care if You’re Pregnant:
Grounding AI Ethics in Empirical Studies},
    author={Bobbie Eicher, Lalith Polepeddi, Ashok Goel},
    booktitle={Proceedings of the First AAAI/ACM Conference on Artificial Intelligence, Ethics & Society},
    year={2018}
}
@inproceedings{cave18risk,
    title={An AI Race for Strategic Advantage: Rhetoric and Risks},
    author={Stephen Cave and Seán S ÓhÉigeartaigh},
  booktitle={Proceedings of the First AAAI/ACM Conference on Artificial Intelligence, Ethics & Society},
  year={2018}
}
@inproceedings{wallach2018agile,
    title={An Agile Ethical/Legal Model for the International and National Governance of AI and Robotics},
    authors={Wendell Wallach and Gary E. Marchant},
    booktitle={Proceedings of the First AAAI/ACM Conference on Artificial Intelligence, Ethics & Society},
    year={2018}
}
@inproceedings{maas18reg,
    title={Regulating for ‘normal AI accidents’— Operational lessons for the responsible governance of AI deployment},
    author={Matthijs M. Maas},
    booktitle={Proceedings of the First AAAI/ACM Conference on Artificial Intelligence, Ethics & Society},
    year={2018}
}   
@inproceedings{katzsemi2018,
  title={Semi-Black Box: Rapid Development of Planning Based Solutions},
  author={Michael Katz*, Dany Moshkovich, Erez Karpas},
  booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}

@article{correa2018generalized,
  title={Generalized Adjustment Under Confounding and Selection Biases},
  author={Correa, Juan D and Tian, Jin and Bareinboim, Elias},
  year={2018}
}
@inproceedings{xiaommc2018,
    title={Memory-Augmented Monte Carlo Tree Search},
    author={Chenjun Xiao and Jincheng Mei and Martin Muller},
    year={2018},
    booktitle={Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence}
}
@inproceedings{abel2018solar, 
title={Bandit-Based Solar Panel Control}, 
author={David Abel and Edward C. Willams and Stephen Brawner and Emily Reif and Michael L. Littman}, 
booktitle={Proceedings of the Thirtieth Conference on Innovative Applications of Artificial Intelligence}, 
year={2018} 
}
@inproceedings{shah2018indi, 
title={A water demand prediction model for Central Indiana}, 
author={Setu Shah, Mahmood Hosseini, Zina Ben-Miled, Rebecca Shafer and Steve Berube}, 
booktitle={Proceedings of the Thirtieth Conference on Innovative Applications of Artificial Intelligence}, 
year={2018} 
}
@inproceedings{Hoshino2018, 
title={Optimal Pricing for Distance-Based Transit Fares}, 
author={Richard Hoshino and Jeneva Beairsto}, 
booktitle={Proceedings of the Thirtieth Conference on Innovative Applications of Artificial Intelligence}, 
year={2018} 
}
@inproceedings{shekhar2018, 
title={Upping the Game of Taxi Driving in the Age of Uber}, 
author={Shashi Shekhar Jha, Shih-Fen Cheng, Meghna Lowalekar, Nicholas Wong Wai Hin, Rishikeshan Rajendram, Tran Trong Khiem, Pradeep Varakantham, Truong Trong Nghia and Firmansyah Rahman}, 
booktitle={Proceedings of the Thirtieth Conference on Innovative Applications of Artificial Intelligence}, 
year={2018} 
}
@inproceedings{dwork2012fairness,
  title={Fairness through awareness},
  author={Dwork, Cynthia and Hardt, Moritz and Pitassi, Toniann and Reingold, Omer and Zemel, Richard},
  booktitle={Proceedings of the 3rd innovations in theoretical computer science conference},
  pages={214--226},
  year={2012},
  organization={ACM}
}
@article{chouldechova2017fair,
  title={Fair prediction with disparate impact: A study of bias in recidivism prediction instruments},
  author={Chouldechova, Alexandra},
  journal={Big data},
  volume={5},
  number={2},
  pages={153--163},
  year={2017},
  publisher={Mary Ann Liebert, Inc. 140 Huguenot Street, 3rd Floor New Rochelle, NY 10801 USA}
}
@article{kleinberg2016inherent,
  title={Inherent trade-offs in the fair determination of risk scores},
  author={Kleinberg, Jon and Mullainathan, Sendhil and Raghavan, Manish},
  journal={arXiv preprint arXiv:1609.05807},
  year={2016}
}
@inproceedings{zemel2013learning,
  title={Learning fair representations},
  author={Zemel, Rich and Wu, Yu and Swersky, Kevin and Pitassi, Toni and Dwork, Cynthia},
  booktitle={International Conference on Machine Learning},
  pages={325--333},
  year={2013}
}
@article{antoniou2017data,
  title={Data Augmentation Generative Adversarial Networks},
  author={Antoniou, Antreas and Storkey, Amos and Edwards, Harrison},
  journal={arXiv preprint arXiv:1711.04340},
  year={2017}
}
@incollection{williams1992simple,
  title={Simple statistical gradient-following algorithms for connectionist reinforcement learning},
  author={Williams, Ronald J},
  booktitle={Reinforcement Learning},
  pages={5--32},
  year={1992},
  publisher={Springer}
}
@article{wang2015dueling,
  title={Dueling network architectures for deep reinforcement learning},
  author={Wang, Ziyu and Schaul, Tom and Hessel, Matteo and Van Hasselt, Hado and Lanctot, Marc and De Freitas, Nando},
  journal={arXiv preprint arXiv:1511.06581},
  year={2015}
}
@inproceedings{hasselt2010double,
  title={Double Q-learning},
  author={Hasselt, Hado V},
  booktitle={Advances in Neural Information Processing Systems},
  pages={2613--2621},
  year={2010}
}
@article{schaul2015prioritized,
  title={Prioritized experience replay},
  author={Schaul, Tom and Quan, John and Antonoglou, Ioannis and Silver, David},
  journal={arXiv preprint arXiv:1511.05952},
  year={2015}
}
@article{fortunato2017noisy,
  title={Noisy networks for exploration},
  author={Fortunato, Meire and Azar, Mohammad Gheshlaghi and Piot, Bilal and Menick, Jacob and Osband, Ian and Graves, Alex and Mnih, Vlad and Munos, Remi and Hassabis, Demis and Pietquin, Olivier and others},
  journal={arXiv preprint arXiv:1706.10295},
  year={2017}
}
@article{bellemare2017distributional,
  title={A distributional perspective on reinforcement learning},
  author={Bellemare, Marc G and Dabney, Will and Munos, R{\'e}mi},
  journal={arXiv preprint arXiv:1707.06887},
  year={2017}
}
@article{sutton1988learning,
  title={Learning to predict by the methods of temporal differences},
  author={Sutton, Richard S},
  journal={Machine learning},
  volume={3},
  number={1},
  pages={9--44},
  year={1988},
  publisher={Springer}
}
@inproceedings{mnih2016asynchronous,
  title={Asynchronous methods for deep reinforcement learning},
  author={Mnih, Volodymyr and Badia, Adria Puigdomenech and Mirza, Mehdi and Graves, Alex and Lillicrap, Timothy and Harley, Tim and Silver, David and Kavukcuoglu, Koray},
  booktitle={International Conference on Machine Learning},
  pages={1928--1937},
  year={2016}
}
@article{eykholt2017note,
  title={Note on Attacking Object Detectors with Adversarial Stickers},
  author={Eykholt, Kevin and Evtimov, Ivan and Fernandes, Earlence and Li, Bo and Song, Dawn and Kohno, Tadayoshi and Rahmati, Amir and Prakash, Atul and Tramer, Florian},
  journal={arXiv preprint arXiv:1712.08062},
  year={2017}
}

@article{goodfellow2014explaining,
  title={Explaining and harnessing adversarial examples},
  author={Goodfellow, Ian J and Shlens, Jonathon and Szegedy, Christian},
  journal={arXiv preprint arXiv:1412.6572},
  year={2014}
}
@article{kolter2017provable,
  title={Provable defenses against adversarial examples via the convex outer adversarial polytope},
  author={Kolter, J Zico and Wong, Eric},
  journal={arXiv preprint arXiv:1711.00851},
  year={2017}
}
@article{roth2004kidney,
  title={Kidney exchange},
  author={Roth, Alvin E and S{\"o}nmez, Tayfun and {\"U}nver, M Utku},
  journal={The Quarterly Journal of Economics},
  volume={119},
  number={2},
  pages={457--488},
  year={2004},
  publisher={MIT Press}
}
@inproceedings{abraham2007clearing,
  title={Clearing algorithms for barter exchange markets: Enabling nationwide kidney exchanges},
  author={Abraham, David J and Blum, Avrim and Sandholm, Tuomas},
  booktitle={Proceedings of the 8th ACM conference on Electronic commerce},
  pages={295--304},
  year={2007},
  organization={ACM}
}
@article{mcdermott1998pddl,
  title={PDDL-the planning domain definition language},
  author={McDermott, Drew and Ghallab, Malik and Howe, Adele and Knoblock, Craig and Ram, Ashwin and Veloso, Manuela and Weld, Daniel and Wilkins, David},
  year={1998}
}
@article{asai2017classical,
  title={Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary},
  author={Asai, Masataro and Fukunaga, Alex},
  journal={arXiv preprint arXiv:1705.00154},
  year={2017}
}
@article{zou2005regularization,
  title={Regularization and variable selection via the elastic net},
  author={Zou, Hui and Hastie, Trevor},
  journal={Journal of the Royal Statistical Society: Series B (Statistical Methodology)},
  volume={67},
  number={2},
  pages={301--320},
  year={2005},
  publisher={Wiley Online Library}
}
@inproceedings{pineda2014planning,
  title={Planning Under Uncertainty Using Reduced Models: Revisiting Determinization.},
  author={Pineda, Luis Enrique and Zilberstein, Shlomo},
  booktitle={ICAPS},
  year={2014}
}
@inproceedings{yoon2007ff,
  title={FF-Replan: A Baseline for Probabilistic Planning.},
  author={Yoon, Sung Wook and Fern, Alan and Givan, Robert},
  booktitle={ICAPS},
  volume={7},
  pages={352--359},
  year={2007}
}
@inproceedings{keren2015goal,
  title={Goal Recognition Design for Non-Optimal Agents.},
  author={Keren, Sarah and Gal, Avigdor and Karpas, Erez},
  booktitle={AAAI},
  pages={3298--3304},
  year={2015}
}
@article{eisenberg2009settlement,
  title={What is the settlement rate and why should we care?},
  author={Eisenberg, Theodore and Lanvers, Charlotte},
  journal={Journal of Empirical Legal Studies},
  volume={6},
  number={1},
  pages={111--146},
  year={2009},
  publisher={Wiley Online Library}
}
@inproceedings{mell2016iago,
  title={IAGO: interactive arbitration guide online},
  author={Mell, Johnathan and Gratch, Jonathan},
  booktitle={Proceedings of the 2016 International Conference on Autonomous Agents \& Multiagent Systems},
  pages={1510--1512},
  year={2016},
  organization={International Foundation for Autonomous Agents and Multiagent Systems}
}
@article{sharon2012meta,
  title={Meta-Agent Conflict-Based Search For Optimal Multi-Agent Path Finding.},
  author={Sharon, Guni and Stern, Roni and Felner, Ariel and Sturtevant, Nathan R},
  journal={SoCS},
  volume={1},
  pages={39--40},
  year={2012}
}
@inproceedings{park2017telling,
  title={Telling stories to robots: The effect of backchanneling on a child's storytelling},
  author={Park, Hae Won and Gelsomini, Mirko and Lee, Jin Joo and Breazeal, Cynthia},
  booktitle={Proceedings of the 2017 ACM/IEEE international conference on human-robot interaction},
  pages={100--108},
  year={2017},
  organization={ACM}
}
@inproceedings{westlund2018measuring,
  title={Measuring young children's long-term relationships with social robots},
  author={Westlund, Jacqueline M Kory and Park, Hae Won and Williams, Randi and Breazeal, Cynthia},
  booktitle={Proceedings of the 17th ACM Conference on Interaction Design and Children},
  pages={207--218},
  year={2018},
  organization={ACM}
}
@article{juba2017precision,
  title={Precision-Recall versus Accuracy and the Role of Large Data Sets},
  author={Juba, Brendan and Le, Hai S},
  journal={AAAI},
  year={2019}
}
@inproceedings{liu2019nearneighbor,
  title={Nearneighbor methods in random preference completion},
  author={Liu, Ao and Wu, Qiong and Zhenming, L and Xia, Lirong},
  booktitle={Proceedings of 33rd AAAI Conference on Artifical Intelligence (AAAI-19)},
  year={2019}
}
@article{katz2017nonparametric,
  title={Nonparametric Preference Completion},
  author={Katz-Samuels, Julian and Scott, Clayton},
  journal={arXiv preprint arXiv:1705.08621},
  year={2017}
}
@article{kaban2019dimension,
  title={Dimension-Free Error Bounds from Random Projections},
  author={Kab{\'a}n, Ata},
  journal={AAAI},
  year={2019}
}
@article{karras2017progressive,
  title={Progressive growing of gans for improved quality, stability, and variation},
  author={Karras, Tero and Aila, Timo and Laine, Samuli and Lehtinen, Jaakko},
  journal={arXiv preprint arXiv:1710.10196},
  year={2017}
}
@inproceedings{goodfellow2014generative,
  title={Generative adversarial nets},
  author={Goodfellow, Ian and Pouget-Abadie, Jean and Mirza, Mehdi and Xu, Bing and Warde-Farley, David and Ozair, Sherjil and Courville, Aaron and Bengio, Yoshua},
  booktitle={Advances in neural information processing systems},
  pages={2672--2680},
  year={2014}
}
@article{zhu2017unpaired,
  title={Unpaired image-to-image translation using cycle-consistent adversarial networks},
  author={Zhu, Jun-Yan and Park, Taesung and Isola, Phillip and Efros, Alexei A},
  journal={arXiv preprint},
  year={2017}
}
@inproceedings{wang2018non,
  title={Non-local neural networks},
  author={Wang, Xiaolong and Girshick, Ross and Gupta, Abhinav and He, Kaiming},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={7794--7803},
  year={2018}
}
@article{brock2018large,
  title={Large scale gan training for high fidelity natural image synthesis},
  author={Brock, Andrew and Donahue, Jeff and Simonyan, Karen},
  journal={arXiv preprint arXiv:1809.11096},
  year={2018}
}
@article{ganin2018synthesizing,
  title={Synthesizing Programs for Images using Reinforced Adversarial Learning},
  author={Ganin, Yaroslav and Kulkarni, Tejas and Babuschkin, Igor and Eslami, SM and Vinyals, Oriol},
  journal={arXiv preprint arXiv:1804.01118},
  year={2018}
}
@article{samuel1959some,
  title={Some studies in machine learning using the game of checkers},
  author={Samuel, Arthur L},
  journal={IBM Journal of research and development},
  volume={3},
  number={3},
  pages={210--229},
  year={1959},
  publisher={IBM}
}
@article{miyato2018virtual,
  title={Virtual adversarial training: a regularization method for supervised and semi-supervised learning},
  author={Miyato, Takeru and Maeda, Shin-ichi and Ishii, Shin and Koyama, Masanori},
  journal={IEEE transactions on pattern analysis and machine intelligence},
  year={2018},
  publisher={IEEE}
}
@article{ganin2016domain,
  title={Domain-adversarial training of neural networks},
  author={Ganin, Yaroslav and Ustinova, Evgeniya and Ajakan, Hana and Germain, Pascal and Larochelle, Hugo and Laviolette, Fran{\c{c}}ois and Marchand, Mario and Lempitsky, Victor},
  journal={The Journal of Machine Learning Research},
  volume={17},
  number={1},
  pages={2096--2030},
  year={2016},
  publisher={JMLR. org}
}
@article{edwards2015censoring,
  title={Censoring representations with an adversary},
  author={Edwards, Harrison and Storkey, Amos},
  journal={arXiv preprint arXiv:1511.05897},
  year={2015}
}
@article{shi2018virtual,
  title={Virtual-Taobao: Virtualizing Real-world Online Retail Environment for Reinforcement Learning},
  author={Shi, Jing-Cheng and Yu, Yang and Da, Qing and Chen, Shi-Yong and Zeng, An-Xiang},
  journal={arXiv preprint arXiv:1805.10000},
  year={2018}
}
@article{zhang2018quota,
  title={QUOTA: The Quantile Option Architecture for Reinforcement Learning},
  author={Zhang, Shangtong and Mavrin, Borislav and Yao, Hengshuai and Kong, Linglong and Liu, Bo},
  journal={arXiv preprint arXiv:1811.02073},
  year={2018}
}
@article{franccois2018combined,
  title={Combined Reinforcement Learning via Abstract Representations},
  author={Fran{\c{c}}ois-Lavet, Vincent and Bengio, Yoshua and Precup, Doina and Pineau, Joelle},
  journal={arXiv preprint arXiv:1809.04506},
  year={2018}
}
@article{he2018detecting,
  title={Detecting Vehicle Illegal Parking Events using Sharing Bikes’ Trajectories},
  author={He, Tianfu and Bao, Jie and Li, Ruiyuan and Ruan, Sijie and Li, Yanhua and Tian, Chao and Zheng, Yu},
  journal={KDD},
  year={2018}
}
@inproceedings{zhang2017deep,
  title={Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction.},
  author={Zhang, Junbo and Zheng, Yu and Qi, Dekang},
  booktitle={AAAI},
  pages={1655--1661},
  year={2017}
}
@inproceedings{zheng2013u,
  title={U-Air: When urban air quality inference meets big data},
  author={Zheng, Yu and Liu, Furui and Hsieh, Hsun-Ping},
  booktitle={Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining},
  pages={1436--1444},
  year={2013},
  organization={ACM}
}
@article{chakraborty2019testing,
  title={On Testing of Uniform Samplers},
  author={Chakraborty, Sourav and Meel, Kuldeep S},
  journal={AAAI},
  year={2019}
}
@article{pitis2019rethinking,
  title={Rethinking the Discount Factor in Reinforcement Learning: A Decision Theoretic Approach},
  author={Pitis, Silviu},
  journal={AAAI},
  year={2019}
}
@article{liao2018finding,
  title={Finding All Bayesian Network Structures within a Factor of Optimal},
  author={Liao, Zhenyu A and Sharma, Charupriya and Cussens, James and van Beek, Peter},
  journal={AAAI},
  year={2019}
}
@article{teyssier2012ordering,
  title={Ordering-based search: A simple and effective algorithm for learning Bayesian networks},
  author={Teyssier, Marc and Koller, Daphne},
  journal={arXiv preprint arXiv:1207.1429},
  year={2012}
}
@inproceedings{ng2000algorithms,
  title={Algorithms for inverse reinforcement learning.},
  author={Ng, Andrew Y and Russell, Stuart J and others},
  booktitle={Icml},
  pages={663--670},
  year={2000}
}
@article{gilpin2007lossless,
  title={Lossless abstraction of imperfect information games},
  author={Gilpin, Andrew and Sandholm, Tuomas},
  journal={Journal of the ACM (JACM)},
  volume={54},
  number={5},
  pages={25},
  year={2007},
  publisher={ACM}
}
@inproceedings{sandholm2012lossy,
  title={Lossy stochastic game abstraction with bounds},
  author={Sandholm, Tuomas and Singh, Satinder},
  booktitle={Proceedings of the 13th ACM Conference on Electronic Commerce},
  pages={880--897},
  year={2012},
  organization={ACM}
}
@inproceedings{waugh2009abstraction,
  title={Abstraction pathologies in extensive games},
  author={Waugh, Kevin and Schnizlein, David and Bowling, Michael and Szafron, Duane},
  booktitle={Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems-Volume 2},
  pages={781--788},
  year={2009},
  organization={International Foundation for Autonomous Agents and Multiagent Systems}
}
@inproceedings{lanctot2009monte,
  title={Monte Carlo sampling for regret minimization in extensive games},
  author={Lanctot, Marc and Waugh, Kevin and Zinkevich, Martin and Bowling, Michael},
  booktitle={Advances in neural information processing systems},
  pages={1078--1086},
  year={2009}
}
@article{farina2018online,
  title={Online convex optimization for sequential decision processes and extensive-form games},
  author={Farina, Gabriele and Kroer, Christian and Sandholm, Tuomas},
  journal={arXiv preprint arXiv:1809.03075},
  year={2018}
}
@article{brown2018depth,
  title={Depth-Limited Solving for Imperfect-Information Games},
  author={Brown, Noam and Sandholm, Tuomas and Amos, Brandon},
  journal={NeurIPS},
  year={2018}
}
@article{pang2018reinforcement,
  title={On reinforcement learning for full-length game of starcraft},
  author={Pang, Zhen-Jia and Liu, Ruo-Ze and Meng, Zhou-Yu and Zhang, Yi and Yu, Yang and Lu, Tong},
  journal={AAAI},
  year={2019}
}
@article{annasamy2018towards,
  title={Towards Better Interpretability in Deep Q-Networks},
  author={Annasamy, Raghuram Mandyam and Sycara, Katia},
  journal={AAAI},
  year={2019}
}
@article{song2018diversity,
  title={Diversity-Driven Extensible Hierarchical Reinforcement Learning},
  author={Song, Yuhang and Wang, Jianyi and Lukasiewicz, Thomas and Xu, Zhenghua and Xu, Mai},
  journal={AAAI},
  year={2019}
}
@article{cobbe2018quantifying,
  title={Quantifying Generalization in Reinforcement Learning},
  author={Cobbe, Karl and Klimov, Oleg and Hesse, Chris and Kim, Taehoon and Schulman, John},
  journal={arXiv preprint arXiv:1812.02341},
  year={2018}
}
@article{zhang2018dissection,
  title={A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning},
  author={Zhang, Amy and Ballas, Nicolas and Pineau, Joelle},
  journal={arXiv preprint arXiv:1806.07937},
  year={2018}
}
@article{shih2019compiling,
  title={Compiling Bayesian Network Classifiers into Decision Graphs},
  author={Shih, Andy and Choi, Arthur and Darwiche, Adnan},
  journal={AAAI},
  year={2019}
}
@incollection{baird1995residual,
  title={Residual algorithms: Reinforcement learning with function approximation},
  author={Baird, Leemon},
  booktitle={Machine Learning Proceedings 1995},
  pages={30--37},
  year={1995},
  publisher={Elsevier}
}
@inproceedings{hebert2018multicalibration,
  title={Multicalibration: Calibration for the (computationally-identifiable) masses},
  author={H{\'e}bert-Johnson, {\'U}rsula and Kim, Michael and Reingold, Omer and Rothblum, Guy},
  booktitle={International Conference on Machine Learning},
  pages={1944--1953},
  year={2018}
}
@inproceedings{kim2018fairness,
  title={Fairness through computationally-bounded awareness},
  author={Kim, Michael and Reingold, Omer and Rothblum, Guy},
  booktitle={Advances in Neural Information Processing Systems},
  pages={4842--4852},
  year={2018}
}
@article{dawid2017individual,
  title={On individual risk},
  author={Dawid, Philip},
  journal={Synthese},
  volume={194},
  number={9},
  pages={3445--3474},
  year={2017},
  publisher={Springer}
}
@article{jost1994role,
  title={The role of stereotyping in system-justification and the production of false consciousness},
  author={Jost, John T and Banaji, Mahzarin R},
  journal={British journal of social psychology},
  volume={33},
  number={1},
  pages={1--27},
  year={1994},
  publisher={Wiley Online Library}
}
@article{kim2019preference,
  title={Preference-Informed Fairness},
  author={Kim, Michael P and Korolova, Aleksandra and Rothblum, Guy N and Yona, Gal},
  journal={arXiv preprint arXiv:1904.01793},
  year={2019}
}
@article{edwards2015censoring,
  title={Censoring representations with an adversary},
  author={Edwards, Harrison and Storkey, Amos},
  journal={arXiv preprint arXiv:1511.05897},
  year={2015}
}
@article{madras2018learning,
  title={Learning adversarially fair and transferable representations},
  author={Madras, David and Creager, Elliot and Pitassi, Toniann and Zemel, Richard},
  journal={arXiv preprint arXiv:1802.06309},
  year={2018}
}
@inproceedings{finn2017model,
  title={Model-agnostic meta-learning for fast adaptation of deep networks},
  author={Finn, Chelsea and Abbeel, Pieter and Levine, Sergey},
  booktitle={Proceedings of the 34th International Conference on Machine Learning-Volume 70},
  pages={1126--1135},
  year={2017},
  organization={JMLR. org}
}
@article{botvinick2019reinforcement,
  title={Reinforcement Learning, Fast and Slow},
  author={Botvinick, Mathew and Ritter, Sam and Wang, Jane X and Kurth-Nelson, Zeb and Blundell, Charles and Hassabis, Demis},
  journal={Trends in cognitive sciences},
  year={2019},
  publisher={Elsevier}
}
@article{daw2014algorithmic,
  title={The algorithmic anatomy of model-based evaluation},
  author={Daw, Nathaniel D and Dayan, Peter},
  journal={Philosophical Transactions of the Royal Society B: Biological Sciences},
  volume={369},
  number={1655},
  pages={20130478},
  year={2014},
  publisher={The Royal Society}
}
@article{saemundsson2018meta,
  title={Meta reinforcement learning with latent variable gaussian processes},
  author={S{\ae}mundsson, Steind{\'o}r and Hofmann, Katja and Deisenroth, Marc Peter},
  journal={arXiv preprint arXiv:1803.07551},
  year={2018}
}
@article{zintgraf2018caml,
  title={CAML: Fast Context Adaptation via Meta-Learning},
  author={Zintgraf, Luisa M and Shiarlis, Kyriacos and Kurin, Vitaly and Hofmann, Katja and Whiteson, Shimon},
  journal={arXiv preprint arXiv:1810.03642},
  year={2018}
}
@inproceedings{johnson2016malmo,
  title={The Malmo Platform for Artificial Intelligence Experimentation.},
  author={Johnson, Matthew and Hofmann, Katja and Hutton, Tim and Bignell, David},
  booktitle={IJCAI},
  pages={4246--4247},
  year={2016}
}
@article{kennedy2006blind,
  title={Blind man draws using diminution in three dimensions},
  author={Kennedy, John M and Juricevic, Igor},
  journal={Psychonomic bulletin \& review},
  volume={13},
  number={3},
  pages={506--509},
  year={2006},
  publisher={Springer}
}
@inproceedings{diuk2008object,
  title={An object-oriented representation for efficient reinforcement learning},
  author={Diuk, Carlos and Cohen, Andre and Littman, Michael L},
  booktitle={Proceedings of the 25th international conference on Machine learning},
  pages={240--247},
  year={2008},
  organization={ACM}
}
@inproceedings{kulkarni2016hierarchical,
  title={Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation},
  author={Kulkarni, Tejas D and Narasimhan, Karthik and Saeedi, Ardavan and Tenenbaum, Josh},
  booktitle={Advances in neural information processing systems},
  pages={3675--3683},
  year={2016}
}
@article{dilokthanakul2019feature,
  title={Feature control as intrinsic motivation for hierarchical reinforcement learning},
  author={Dilokthanakul, Nat and Kaplanis, Christos and Pawlowski, Nick and Shanahan, Murray},
  journal={IEEE transactions on neural networks and learning systems},
  year={2019},
  publisher={IEEE}
}
@article{silver2018general,
  title={A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play},
  author={Silver, David and Hubert, Thomas and Schrittwieser, Julian and Antonoglou, Ioannis and Lai, Matthew and Guez, Arthur and Lanctot, Marc and Sifre, Laurent and Kumaran, Dharshan and Graepel, Thore and others},
  journal={Science},
  volume={362},
  number={6419},
  pages={1140--1144},
  year={2018},
  publisher={American Association for the Advancement of Science}
}
@inproceedings{chua2018deep,
  title={Deep reinforcement learning in a handful of trials using probabilistic dynamics models},
  author={Chua, Kurtland and Calandra, Roberto and McAllister, Rowan and Levine, Sergey},
  booktitle={Advances in Neural Information Processing Systems},
  pages={4754--4765},
  year={2018}
}
@article{hafner2018learning,
  title={Learning latent dynamics for planning from pixels},
  author={Hafner, Danijar and Lillicrap, Timothy and Fischer, Ian and Villegas, Ruben and Ha, David and Lee, Honglak and Davidson, James},
  journal={arXiv preprint arXiv:1811.04551},
  year={2018}
}
@inproceedings{harutyunyan2018learning,
  title={Learning with options that terminate off-policy},
  author={Harutyunyan, Anna and Vrancx, Peter and Bacon, Pierre-Luc and Precup, Doina and Now{\'e}, Ann},
  booktitle={Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
@article{harutyunyan2019termination,
  title={The Termination Critic},
  author={Harutyunyan, Anna and Dabney, Will and Borsa, Diana and Heess, Nicolas and Munos, Remi and Precup, Doina},
  journal={arXiv preprint arXiv:1902.09996},
  year={2019}
}
@article{berlyne1960conflict,
  title={Conflict, arousal, and curiosity.},
  author={Berlyne, Daniel E},
  year={1960},
  publisher={McGraw-Hill Book Company}
}
@article{berlyne1978curiosity,
  title={Curiosity and learning},
  author={Berlyne, Daniel E},
  journal={Motivation and emotion},
  volume={2},
  number={2},
  pages={97--175},
  year={1978},
  publisher={Springer}
}
@incollection{oudeyer2016intrinsic,
  title={Intrinsic motivation, curiosity, and learning: Theory and applications in educational technologies},
  author={Oudeyer, P-Y and Gottlieb, Jacqueline and Lopes, Manuel},
  booktitle={Progress in brain research},
  volume={229},
  pages={257--284},
  year={2016},
  publisher={Elsevier}
}
@article{laversanne2018curiosity,
  title={Curiosity driven exploration of learned disentangled goal spaces},
  author={Laversanne-Finot, Adrien and P{\'e}r{\'e}, Alexandre and Oudeyer, Pierre-Yves},
  journal={arXiv preprint arXiv:1807.01521},
  year={2018}
}
@book{oudeyer2006self,
  title={Self-organization in the evolution of speech},
  author={Oudeyer, Pierre-Yves},
  volume={6},
  number={6},
  year={2006},
  publisher={OUP Oxford}
}
@article{hjelm2018learning,
  title={Learning deep representations by mutual information estimation and maximization},
  author={Hjelm, R Devon and Fedorov, Alex and Lavoie-Marchildon, Samuel and Grewal, Karan and Trischler, Adam and Bengio, Yoshua},
  journal={arXiv preprint arXiv:1808.06670},
  year={2018}
}
@inproceedings{li2018smoothing,
  title={Smoothing the Geometry of Probabilistic Box Embeddings},
  author={Li, Xiang and Vilnis, Luke and Zhang, Dongxu and Boratko, Michael and McCallum, Andrew},
  year={2019},
  booktitle={ICLR}
}
@article{mao2019neuro,
  title={The Neuro-Symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision},
  author={Mao, Jiayuan and Gan, Chuang and Kohli, Pushmeet and Tenenbaum, Joshua B and Wu, Jiajun},
  journal={arXiv preprint arXiv:1904.12584},
  year={2019}
}
@article{wu2019pay,
  title={Pay Less Attention with Lightweight and Dynamic Convolutions},
  author={Wu, Felix and Fan, Angela and Baevski, Alexei and Dauphin, Yann N and Auli, Michael},
  journal={arXiv preprint arXiv:1901.10430},
  year={2019}
}
@article{shen2019ordered,
  title={Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks},
  author={Shen, Yikang and Tan, Shawn and Sordoni, Alessandro and Courville, Aaron},
  journal={Proceedings of ICLR},
  year={2019}
}
@inproceedings{nachum2018near,
  title={Near-Optimal Representation Learning for Hierarchical Reinforcement Learning},
  author={Nachum, Ofir and Gu, Shixiang and Lee, Honglak and Levine, Sergey},
  booktitle={ICLR},
  year={2019}
}
@inproceedings{levy2018learning,
  title={Learning Multi-Level Hierarchies with Hindsight},
  author={Levy, Andrew and Konidaris, George and Platt, Robert and Saenko, Kate},
  booktitle={ICLR},
  year={2019}
}
@inproceedings{koul2018learning,
  title={Learning Finite State Representations of Recurrent Policy Networks},
  author={Koul, Anurag and Greydanus, Sam and Fern, Alan},
  inproceedings={ICLR},
  year={2019}
}
@inproceedings{shawe1997pac,
  title={A PAC analysis of a Bayesian estimator},
  author={Shawe-Taylor, John and Williamson, Robert C},
  booktitle={Annual Workshop on Computational Learning Theory: Proceedings of the tenth annual conference on Computational learning theory},
  volume={6},
  number={09},
  pages={2--9},
  year={1997}
}
@article{mcallester1999some,
  title={Some pac-bayesian theorems},
  author={McAllester, David A},
  journal={Machine Learning},
  volume={37},
  number={3},
  pages={355--363},
  year={1999},
  publisher={Springer}
}
@inproceedings{valiant1984theory,
  title={A theory of the learnable},
  author={Valiant, Leslie G},
  booktitle={Proceedings of the sixteenth annual ACM symposium on Theory of computing},
  pages={436--445},
  year={1984},
  organization={ACM}
}
@inproceedings{fard2010pac,
  title={PAC-Bayesian model selection for reinforcement learning},
  author={Fard, Mahdi M and Pineau, Joelle},
  booktitle={Advances in Neural Information Processing Systems},
  pages={1624--1632},
  year={2010}
}
@inproceedings{ambroladze2007tighter,
  title={Tighter pac-bayes bounds},
  author={Ambroladze, Amiran and Parrado-Hern{\'a}ndez, Emilio and Shawe-taylor, John S},
  booktitle={Advances in neural information processing systems},
  pages={9--16},
  year={2007}
}
@article{csiszar1975divergence,
  title={I-divergence geometry of probability distributions and minimization problems},
  author={Csisz{\'a}r, Imre},
  journal={The Annals of Probability},
  pages={146--158},
  year={1975},
  publisher={JSTOR}
}
@article{catoni2007pac,
  title={PAC-Bayesian supervised classification: the thermodynamics of statistical learning},
  author={Catoni, Olivier},
  journal={arXiv preprint arXiv:0712.0248},
  year={2007}
}
@article{bousquet2002stability,
  title={Stability and generalization},
  author={Bousquet, Olivier and Elisseeff, Andr{\'e}},
  journal={Journal of machine learning research},
  volume={2},
  number={Mar},
  pages={499--526},
  year={2002}
}
@inproceedings{belkin2018overfitting,
  title={Overfitting or perfect fitting? risk bounds for classification and regression rules that interpolate},
  author={Belkin, Mikhail and Hsu, Daniel J and Mitra, Partha},
  booktitle={Advances in Neural Information Processing Systems},
  pages={2300--2311},
  year={2018}
}
@article{dziugaite2017entropy,
  title={Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors},
  author={Dziugaite, Gintare Karolina and Roy, Daniel M},
  journal={arXiv preprint arXiv:1712.09376},
  year={2017}
}
@article{achille2018information,
  title={Information dropout: Learning optimal representations through noisy computation},
  author={Achille, Alessandro and Soatto, Stefano},
  journal={IEEE transactions on pattern analysis and machine intelligence},
  volume={40},
  number={12},
  pages={2897--2905},
  year={2018},
  publisher={IEEE}
}
@article{lake2015human,
  title={Human-level concept learning through probabilistic program induction},
  author={Lake, Brenden M and Salakhutdinov, Ruslan and Tenenbaum, Joshua B},
  journal={Science},
  volume={350},
  number={6266},
  pages={1332--1338},
  year={2015},
  publisher={American Association for the Advancement of Science}
}
@inproceedings{liu2016stein,
  title={Stein variational gradient descent: A general purpose bayesian inference algorithm},
  author={Liu, Qiang and Wang, Dilin},
  booktitle={Advances In Neural Information Processing Systems},
  pages={2378--2386},
  year={2016}
}
@article{garnelo2018conditional,
  title={Conditional neural processes},
  author={Garnelo, Marta and Rosenbaum, Dan and Maddison, Chris J and Ramalho, Tiago and Saxton, David and Shanahan, Murray and Teh, Yee Whye and Rezende, Danilo J and Eslami, SM},
  journal={arXiv preprint arXiv:1807.01613},
  year={2018}
}
@article{kim2018bayesian,
  title={Bayesian model-agnostic meta-learning},
  author={Kim, Taesup and Yoon, Jaesik and Dia, Ousmane and Kim, Sungwoong and Bengio, Yoshua and Ahn, Sungjin},
  journal={arXiv preprint arXiv:1806.03836},
  year={2018}
}
@article{ravi2018amortized,
  title={Amortized Bayesian Meta-Learning},
  author={Ravi, Sachin and Beatson, Alex},
  year={2018}
}
@incollection{littman1994markov,
  title={Markov games as a framework for multi-agent reinforcement learning},
  author={Littman, Michael L},
  booktitle={Machine learning proceedings 1994},
  pages={157--163},
  year={1994},
  publisher={Elsevier}
}
@article{haarnoja2018soft,
  title={Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor},
  author={Haarnoja, Tuomas and Zhou, Aurick and Abbeel, Pieter and Levine, Sergey},
  journal={arXiv preprint arXiv:1801.01290},
  year={2018}
}
@article{peng2019domain,
  title={Domain Agnostic Learning with Disentangled Representations},
  author={Peng, Xingchao and Huang, Zijun and Sun, Ximeng and Saenko, Kate},
  journal={arXiv preprint arXiv:1904.12347},
  year={2019}
}
@inproceedings{saito2018maximum,
  title={Maximum classifier discrepancy for unsupervised domain adaptation},
  author={Saito, Kuniaki and Watanabe, Kohei and Ushiku, Yoshitaka and Harada, Tatsuya},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={3723--3732},
  year={2018}
}
@article{ganin2016domain,
  title={Domain-adversarial training of neural networks},
  author={Ganin, Yaroslav and Ustinova, Evgeniya and Ajakan, Hana and Germain, Pascal and Larochelle, Hugo and Laviolette, Fran{\c{c}}ois and Marchand, Mario and Lempitsky, Victor},
  journal={The Journal of Machine Learning Research},
  volume={17},
  number={1},
  pages={2096--2030},
  year={2016},
  publisher={JMLR. org}
}
@inproceedings{tzeng2017adversarial,
  title={Adversarial discriminative domain adaptation},
  author={Tzeng, Eric and Hoffman, Judy and Saenko, Kate and Darrell, Trevor},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={7167--7176},
  year={2017}
}
@article{ernst2005tree,
  title={Tree-based batch mode reinforcement learning},
  author={Ernst, Damien and Geurts, Pierre and Wehenkel, Louis},
  journal={Journal of Machine Learning Research},
  volume={6},
  number={Apr},
  pages={503--556},
  year={2005}
}
@article{kuleshov2018accurate,
  title={Accurate uncertainties for deep learning using calibrated regression},
  author={Kuleshov, Volodymyr and Fenner, Nathan and Ermon, Stefano},
  journal={arXiv preprint arXiv:1807.00263},
  year={2018}
}
@inproceedings{chua2018deep,
  title={Deep reinforcement learning in a handful of trials using probabilistic dynamics models},
  author={Chua, Kurtland and Calandra, Roberto and McAllister, Rowan and Levine, Sergey},
  booktitle={Advances in Neural Information Processing Systems},
  pages={4754--4765},
  year={2018}
}
@inproceedings{roulet2019iterative,
  title={Iterative Linearized Control: Stable Algorithms and Complexity Guarantees},
  author={Roulet, Vincent and Drusvyatskiy, Dmitriy and Srinivasa, Siddhartha and Harchaoui, Zaid},
  booktitle={International Conference on Machine Learning},
  pages={5518--5527},
  year={2019}
}
@inproceedings{jinnai2019finding,
  title={Finding Options that Minimize Planning Time},
  author={Jinnai, Yuu and Abel, David and Littman, Michael and Konidaris, George},
  booktitle={International Conference on Machine Learning},
  year={2019}
}
@inproceedings{arpit2017closer,
  title={A closer look at memorization in deep networks},
  author={Arpit, Devansh and Jastrz{\k{e}}bski, Stanis{\l}aw and Ballas, Nicolas and Krueger, David and Bengio, Emmanuel and Kanwal, Maxinder S and Maharaj, Tegan and Fischer, Asja and Courville, Aaron and Bengio, Yoshua and others},
  booktitle={Proceedings of the 34th International Conference on Machine Learning-Volume 70},
  pages={233--242},
  year={2017},
  organization={JMLR. org}
}
@article{rahaman2018spectral,
  title={On the Spectral Bias of Neural Networks},
  author={Rahaman, Nasim and Baratin, Aristide and Arpit, Devansh and Draxler, Felix and Lin, Min and Hamprecht, Fred and Bengio, Yoshua and Courville, Aaron},
  year={2018}
}
@article{le2019batch,
  title={Batch Policy Learning under Constraints},
  author={Le, Hoang M and Voloshin, Cameron and Yue, Yisong},
  journal={arXiv preprint arXiv:1903.08738},
  year={2019}
}
@inproceedings{reddy2018ask,
  title={Ask, Acquire, and Attack: Data-free UAP Generation using Class Impressions},
  author={Reddy Mopuri, Konda and Krishna Uppala, Phani and Venkatesh Babu, R},
  booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
  pages={19--34},
  year={2018}
}
@article{nayak2019zero,
  title={Zero-Shot Knowledge Distillation in Deep Networks},
  author={Nayak, Gaurav Kumar and Mopuri, Konda Reddy and Shaj, Vaisakh and Babu, R Venkatesh and Chakraborty, Anirban},
  journal={arXiv preprint arXiv:1905.08114},
  year={2019}
}
@article{platt2017analyzing,
  title={Analyzing energy technologies and policies using DOSCOE},
  author={Platt, John and Pritchard, J and Bryant, Drew},
  year={2017}
}
@article{o2018using,
  title={Using Machine Learning to Parameterize Moist Convection: Potential for Modeling of Climate, Climate Change, and Extreme Events},
  author={O'Gorman, Paul A and Dwyer, John G},
  journal={Journal of Advances in Modeling Earth Systems},
  volume={10},
  number={10},
  pages={2548--2563},
  year={2018},
  publisher={Wiley Online Library}
}
@article{wang2019machine,
  title={Machine Vision for Natural Gas Methane Emissions Detection Using an Infrared Camera},
  author={Wang, Jingfan and Tchapmi, Lyne P and Ravikumara, Arvind P and McGuire, Mike and Bell, Clay S and Zimmerle, Daniel and Savarese, Silvio and Brandt, Adam R},
  journal={arXiv preprint arXiv:1904.08500},
  year={2019}
}
@article{diffenbaugh2019global,
  title={Global warming has increased global economic inequality},
  author={Diffenbaugh, Noah S and Burke, Marshall},
  journal={Proceedings of the National Academy of Sciences},
  volume={116},
  number={20},
  pages={9808--9813},
  year={2019},
  publisher={National Acad Sciences}
}
@book{pearl2018book,
  title={The book of why: the new science of cause and effect},
  author={Pearl, Judea and Mackenzie, Dana},
  year={2018},
  publisher={Basic Books}
}
@inproceedings{jacq2019learning,
  title={Learning from a Learner},
  author={Jacq, Alexis and Geist, Matthieu and Paiva, Ana and Pietquin, Olivier},
  booktitle={International Conference on Machine Learning},
  pages={2990--2999},
  year={2019}
}
@article{chandak2019learning,
  title={Learning Action Representations for Reinforcement Learning},
  author={Chandak, Yash and Theocharous, Georgios and Kostas, James and Jordan, Scott and Thomas, Philip S},
  journal={arXiv preprint arXiv:1902.00183},
  year={2019}
}
@article{london2018bayesian,
  title={Bayesian Counterfactual Risk Minimization},
  author={London, Ben and Sandler, Ted},
  journal={arXiv preprint arXiv:1806.11500},
  year={2018}
}
@inproceedings{harutyunyan2019per,
  title={Per-Decision Option Discounting},
  author={Harutyunyan, Anna and Vrancx, Peter and Hamel, Philippe and Nowe, Ann and Precup, Doina},
  booktitle={International Conference on Machine Learning},
  pages={2644--2652},
  year={2019}
}
@article{zanette2019tighter,
  title={Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds},
  author={Zanette, Andrea and Brunskill, Emma},
  journal={arXiv preprint arXiv:1901.00210},
  year={2019}
}
@article{geist2019theory,
  title={A Theory of Regularized Markov Decision Processes},
  author={Geist, Matthieu and Scherrer, Bruno and Pietquin, Olivier},
  journal={arXiv preprint arXiv:1901.11275},
  year={2019}
}
@inproceedings{jinnai2019discovering,
  title={Discovering Options for Exploration by Minimizing Cover Time},
  author={Jinnai, Yuu and Park, Jee Won and Abel, David and Konidaris, George},
  booktitle={International Conference on Machine Learning},
  year={2019}
}
@article{dann2018policy,
  title={Policy certificates: Towards accountable reinforcement learning},
  author={Dann, Christoph and Li, Lihong and Wei, Wei and Brunskill, Emma},
  journal={arXiv preprint arXiv:1811.03056},
  year={2018}
}
@article{locatello2018challenging,
  title={Challenging common assumptions in the unsupervised learning of disentangled representations},
  author={Locatello, Francesco and Bauer, Stefan and Lucic, Mario and Gelly, Sylvain and Sch{\"o}lkopf, Bernhard and Bachem, Olivier},
  journal={arXiv preprint arXiv:1811.12359},
  year={2018}
}
@article{qu2018nonlinear,
  title={Nonlinear Distributional Gradient Temporal-Difference Learning},
  author={Qu, Chao and Mannor, Shie and Xu, Huan},
  journal={arXiv preprint arXiv:1805.07732},
  year={2018}
}
@article{hunt2018composing,
  title={Composing Entropic Policies using Divergence Correction},
  author={Hunt, Jonathan J and Barreto, Andre and Lillicrap, Timothy P and Heess, Nicolas},
  year={2018}
}
@inproceedings{yu2019multi,
  title={Multi-Agent Adversarial Inverse Reinforcement Learning},
  author={Yu, Lantao and Song, Jiaming and Ermon, Stefano},
  booktitle={International Conference on Machine Learning},
  pages={7194--7201},
  year={2019}
}
@article{kaplanis2019policy,
  title={Policy Consolidation for Continual Reinforcement Learning},
  author={Kaplanis, Christos and Shanahan, Murray and Clopath, Claudia},
  journal={arXiv preprint arXiv:1902.00255},
  year={2019}
}
@article{fujimoto2018off,
  title={Off-Policy Deep Reinforcement Learning without Exploration},
  author={Fujimoto, Scott and Meger, David and Precup, Doina},
  journal={arXiv preprint arXiv:1812.02900},
  year={2018}
}
@article{wang2019random,
  title={Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation},
  author={Wang, Ruohan and Ciliberto, Carlo and Amadori, Pierluigi and Demiris, Yiannis},
  journal={arXiv preprint arXiv:1905.06750},
  year={2019}
}
@inproceedings{song2019revisiting,
  title={Revisiting the Softmax Bellman Operator: New Benefits and New Perspective},
  author={Song, Zhao and Parr, Ron and Carin, Lawrence},
  booktitle={International Conference on Machine Learning},
  pages={5916--5925},
  year={2019}
}
@article{mavrin2019distributional,
  title={Distributional Reinforcement Learning for Efficient Exploration},
  author={Mavrin, Borislav and Zhang, Shangtong and Yao, Hengshuai and Kong, Linglong and Wu, Kaiwen and Yu, Yaoliang},
  journal={arXiv preprint arXiv:1905.06125},
  year={2019}
}
@inproceedings{papini2019optimistic,
  title={Optimistic Policy Optimization via Multiple Importance Sampling},
  author={Papini, Matteo and Metelli, Alberto Maria and Lupo, Lorenzo and Restelli, Marcello},
  booktitle={International Conference on Machine Learning},
  pages={4989--4999},
  year={2019}
}
@article{jiang2019neural,
  title={Neural Logic Reinforcement Learning},
  author={Jiang, Zhengyao and Luo, Shan},
  journal={arXiv preprint arXiv:1904.10729},
  year={2019}
}
@article{radanovic2019learning,
  title={Learning to Collaborate in Markov Decision Processes},
  author={Radanovic, Goran and Devidze, Rati and Parkes, David and Singla, Adish},
  journal={arXiv preprint arXiv:1901.08029},
  year={2019}
}
@article{cheng2018predictor,
  title={Predictor-Corrector Policy Optimization},
  author={Cheng, Ching-An and Yan, Xinyan and Ratliff, Nathan and Boots, Byron},
  journal={arXiv preprint arXiv:1810.06509},
  year={2018}
}
@article{xu2018learning,
  title={Learning a prior over intent via meta-inverse reinforcement learning},
  author={Xu, Kelvin and Ratner, Ellis and Dragan, Anca and Levine, Sergey and Finn, Chelsea},
  journal={arXiv preprint arXiv:1805.12573},
  year={2018}
}
@article{gelada2019deepmdp,
  title={DeepMDP: Learning Continuous Latent Space Models for Representation Learning},
  author={Gelada, Carles and Kumar, Saurabh and Buckman, Jacob and Nachum, Ofir and Bellemare, Marc G},
  journal={arXiv preprint arXiv:1906.02736},
  year={2019}
}
@article{hanna2018importance,
  title={Importance sampling policy evaluation with an estimated behavior policy},
  author={Hanna, Josiah and Niekum, Scott and Stone, Peter},
  journal={arXiv preprint arXiv:1806.01347},
  year={2018}
}
@article{tessler2019action,
  title={Action Robust Reinforcement Learning and Applications in Continuous Control},
  author={Tessler, Chen and Efroni, Yonathan and Mannor, Shie},
  journal={arXiv preprint arXiv:1901.09184},
  year={2019}
}
@article{dadashi2019value,
  title={The Value Function Polytope in Reinforcement Learning},
  author={Dadashi, Robert and Ta{\"\i}ga, Adrien Ali and Roux, Nicolas Le and Schuurmans, Dale and Bellemare, Marc G},
  journal={arXiv preprint arXiv:1901.11524},
  year={2019}
}
@article{tallec2019making,
  title={Making Deep Q-learning methods robust to time discretization},
  author={Tallec, Corentin and Blier, L{\'e}onard and Ollivier, Yann},
  journal={arXiv preprint arXiv:1901.09732},
  year={2019}
}
@article{qu2018nonlinear,
  title={Nonlinear Distributional Gradient Temporal-Difference Learning},
  author={Qu, Chao and Mannor, Shie and Xu, Huan},
  journal={arXiv preprint arXiv:1805.07732},
  year={2018}
}
@article{hunt2018composing,
  title={Composing Entropic Policies using Divergence Correction},
  author={Hunt, Jonathan J and Barreto, Andre and Lillicrap, Timothy P and Heess, Nicolas},
  year={2018}
}
@inproceedings{adel2019tibgm,
  title={TibGM: A Transferable and Information-Based Graphical Model Approach for Reinforcement Learning},
  author={Adel, Tameem and Weller, Adrian},
  booktitle={International Conference on Machine Learning},
  pages={71--81},
  year={2019}
}
@inproceedings{van2019composing,
  title={Composing Value Functions in Reinforcement Learning},
  author={Van Niekerk, Benjamin and James, Steven and Earle, Adam and Rosman, Benjamin},
  booktitle={International Conference on Machine Learning},
  pages={6401--6409},
  year={2019}
}
@inproceedings{zintgraf2019fast,
  title={Fast Context Adaptation via Meta-Learning},
  author={Zintgraf, Luisa and Shiarli, Kyriacos and Kurin, Vitaly and Hofmann, Katja and Whiteson, Shimon},
  booktitle={International Conference on Machine Learning},
  pages={7693--7702},
  year={2019}
}
@article{khodak2019adaptive,
  title={Adaptive Gradient-Based Meta-Learning Methods},
  author={Khodak, Mikhail and Florina-Balcan, Maria and Talwalkar, Ameet},
  journal={arXiv preprint arXiv:1906.02717},
  year={2019}
}
@inproceedings{phuong2019towards,
  title={Towards Understanding Knowledge Distillation},
  author={Phuong, Mary and Lampert, Christoph},
  booktitle={International Conference on Machine Learning},
  pages={5142--5151},
  year={2019}
}
@inproceedings{liu2019transferable,
  title={Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers},
  author={Liu, Hong and Long, Mingsheng and Wang, Jianmin and Jordan, Michael},
  booktitle={International Conference on Machine Learning},
  pages={4013--4022},
  year={2019}
}
@article{sun2019provably,
  title={Provably Efficient Imitation Learning from Observation Alone},
  author={Sun, Wen and Vemula, Anirudh and Boots, Byron and Bagnell, J Andrew},
  journal={arXiv preprint arXiv:1905.10948},
  year={2019}
}
@inproceedings{fatemi2019dead,
  title={Dead-ends and Secure Exploration in Reinforcement Learning},
  author={Fatemi, Mehdi and Sharma, Shikhar and Van Seijen, Harm and Kahou, Samira Ebrahimi},
  booktitle={International Conference on Machine Learning},
  pages={1873--1881},
  year={2019}
}
@article{rowland2019statistics,
  title={Statistics and Samples in Distributional Reinforcement Learning},
  author={Rowland, Mark and Dadashi, Robert and Kumar, Saurabh and Munos, R{\'e}mi and Bellemare, Marc G and Dabney, Will},
  journal={arXiv preprint arXiv:1902.08102},
  year={2019}
}
@inproceedings{shen2019hessian,
  title={Hessian Aided Policy Gradient},
  author={Shen, Zebang and Ribeiro, Alejandro and Hassani, Hamed and Qian, Hui and Mi, Chao},
  booktitle={International Conference on Machine Learning},
  pages={5729--5738},
  year={2019}
}
@article{hazan2018provably,
  title={Provably efficient maximum entropy exploration},
  author={Hazan, Elad and Kakade, Sham M and Singh, Karan and Van Soest, Abby},
  journal={arXiv preprint arXiv:1812.02690},
  year={2018}
}
@article{gottesman2019combining,
  title={Combining parametric and nonparametric models for off-policy evaluation},
  author={Gottesman, Omer and Liu, Yao and Sussex, Scott and Brunskill, Emma and Doshi-Velez, Finale},
  journal={arXiv preprint arXiv:1905.05787},
  year={2019}
}
@inproceedings{yang2019sample,
  title={Sample-Optimal Parametric Q-Learning Using Linearly Additive Features},
  author={Yang, Lin and Wang, Mengdi},
  booktitle={International Conference on Machine Learning},
  pages={6995--7004},
  year={2019}
}
@inproceedings{tirinzoni2019transfer,
  title={Transfer of Samples in Policy Search via Multiple Importance Sampling},
  author={Tirinzoni, Andrea and Salvini, Mattia and Restelli, Marcello},
  booktitle={International Conference on Machine Learning},
  pages={6264--6274},
  year={2019}
}
@inproceedings{shani2019exploration,
  title={Exploration Conscious Reinforcement Learning Revisited},
  author={Shani, Lior and Efroni, Yonathan and Mannor, Shie},
  booktitle={International Conference on Machine Learning},
  pages={5680--5689},
  year={2019}
}
@inproceedings{lim2019kernel,
  title={Kernel-Based Reinforcement Learning in Robust Markov Decision Processes},
  author={Lim, Shiau Hong and Autef, Arnaud},
  booktitle={International Conference on Machine Learning},
  pages={3973--3981},
  year={2019}
}
@article{cobbe2018quantifying,
  title={Quantifying generalization in reinforcement learning},
  author={Cobbe, Karl and Klimov, Oleg and Hesse, Chris and Kim, Taehoon and Schulman, John},
  journal={arXiv preprint arXiv:1812.02341},
  year={2018}
}
@article{hafner2018learning,
  title={Learning latent dynamics for planning from pixels},
  author={Hafner, Danijar and Lillicrap, Timothy and Fischer, Ian and Villegas, Ruben and Ha, David and Lee, Honglak and Davidson, James},
  journal={arXiv preprint arXiv:1811.04551},
  year={2018}
}
@inproceedings{akrour2019projections,
  title={Projections for Approximate Policy Iteration Algorithms},
  author={Akrour, Riad and Pajarinen, Joni and Peters, Jan and Neumann, Gerhard},
  booktitle={International Conference on Machine Learning},
  pages={181--190},
  year={2019}
}
@inproceedings{innes2019learning,
  title={Learning Structured Decision Problems with Unawareness},
  author={Innes, Craig and Lascarides, Alex},
  booktitle={International Conference on Machine Learning},
  pages={2941--2950},
  year={2019}
}
@inproceedings{malik2019calibrated,
  title={Calibrated Model-Based Deep Reinforcement Learning},
  author={Malik, Ali and Kuleshov, Volodymyr and Song, Jiaming and Nemer, Danny and Seymour, Harlan and Ermon, Stefano},
  booktitle={International Conference on Machine Learning},
  pages={4314--4323},
  year={2019}
}
@inproceedings{metelli2019reinforcement,
  title={Reinforcement Learning in Configurable Continuous Environments},
  author={Metelli, Alberto Maria and Ghelfi, Emanuele and Restelli, Marcello},
  booktitle={International Conference on Machine Learning},
  pages={4546--4555},
  year={2019}
}
@article{lee2019target,
  title={Target-Based Temporal Difference Learning},
  author={Lee, Donghwan and He, Niao},
  journal={arXiv preprint arXiv:1904.10945},
  year={2019}
}
@inproceedings{brutzkus2019larger,
  title={Why do Larger Models Generalize Better? A Theoretical Perspective via the XOR Problem},
  author={Brutzkus, Alon and Globerson, Amir},
  booktitle={International Conference on Machine Learning},
  pages={822--830},
  year={2019}
}
@article{ghazi2019recursive,
  title={Recursive Sketches for Modular Deep Learning},
  author={Ghazi, Badih and Panigrahy, Rina and Wang, Joshua R},
  journal={arXiv preprint arXiv:1905.12730},
  year={2019}
}
@article{allen2018convergence,
  title={A convergence theory for deep learning via over-parameterization},
  author={Allen-Zhu, Zeyuan and Li, Yuanzhi and Song, Zhao},
  journal={arXiv preprint arXiv:1811.03962},
  year={2018}
}
@article{romoff2019separating,
  title={Separating value functions across time-scales},
  author={Romoff, Joshua and Henderson, Peter and Touati, Ahmed and Ollivier, Yann and Brunskill, Emma and Pineau, Joelle},
  journal={arXiv preprint arXiv:1902.01883},
  year={2019}
}
@inproceedings{vinyals2016matching,
  title={Matching networks for one shot learning},
  author={Vinyals, Oriol and Blundell, Charles and Lillicrap, Timothy and Wierstra, Daan and others},
  booktitle={Advances in neural information processing systems},
  pages={3630--3638},
  year={2016}
}
@inproceedings{barreto2017successor,
  title={Successor features for transfer in reinforcement learning},
  author={Barreto, Andr{\'e} and Dabney, Will and Munos, R{\'e}mi and Hunt, Jonathan J and Schaul, Tom and van Hasselt, Hado P and Silver, David},
  booktitle={Advances in neural information processing systems},
  pages={4055--4065},
  year={2017}
}
@inproceedings{haarnoja2018composable,
  title={Composable deep reinforcement learning for robotic manipulation},
  author={Haarnoja, Tuomas and Pong, Vitchyr and Zhou, Aurick and Dalal, Murtaza and Abbeel, Pieter and Levine, Sergey},
  booktitle={2018 IEEE International Conference on Robotics and Automation (ICRA)},
  pages={6244--6251},
  year={2018},
  organization={IEEE}
}
@inproceedings{asadi2017alternative,
  title={An alternative softmax operator for reinforcement learning},
  author={Asadi, Kavosh and Littman, Michael L},
  booktitle={Proceedings of the 34th International Conference on Machine Learning-Volume 70},
  pages={243--252},
  year={2017},
  organization={JMLR. org}
}
@article{ravi2018amortized,
  title={Amortized Bayesian Meta-Learning},
  author={Ravi, Sachin and Beatson, Alex},
  year={2018}
}