-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
ca34d5f
commit 799b8e3
Showing
51 changed files
with
739 additions
and
0 deletions.
There are no files selected for viewing
33 changes: 33 additions & 0 deletions
33
env_acrobot_swingup/Dyna/DynaSAC_Bounded_Yao/alg_config.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,33 @@ | ||
| { | ||
| "algorithm": "DynaSAC_Bounded_Yao", | ||
| "type": "mbrl", | ||
| "G": 1, | ||
| "G_model": 5.0, | ||
| "batch_size": 256, | ||
| "buffer_size": 1000000, | ||
| "max_steps_exploration": 256, | ||
| "max_steps_training": 1000000, | ||
| "number_steps_per_train_policy": 1, | ||
|
|
||
| "reward_scale": 1.0, | ||
| "actor_lr": 3e-4, | ||
| "critic_lr": 3e-4, | ||
| "alpha_lr": 3e-4, | ||
| "gamma": 0.99, | ||
| "tau": 0.005, | ||
|
|
||
| "min_noise": 0.0, | ||
| "noise_scale": 0.1, | ||
| "noise_decay": 1.0, | ||
|
|
||
| "num_models": 6, | ||
| "world_model_lr": 0.001, | ||
| "horizon": 1, | ||
| "num_samples": 10, | ||
| "sas": false, | ||
| "train_reward": true, | ||
| "train_both": false, | ||
| "gripper": false, | ||
| "threshold": 1.0, | ||
| "exploration_sample": 2 | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| { | ||
| "gym": "dmcs", | ||
| "task": "swingup", | ||
| "domain": "acrobot" | ||
| } |
5 changes: 5 additions & 0 deletions
5
env_acrobot_swingup/Dyna/DynaSAC_Bounded_Yao/train_config.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| { | ||
| "seeds": [15, 25, 35, 45, 55], | ||
| "number_steps_per_evaluation": 10000, | ||
| "number_eval_episodes": 10 | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,34 @@ | ||
| { | ||
| "algorithm": "STEVESAC_Bounded_Yao", | ||
| "type": "mbrl", | ||
| "G": 1, | ||
| "G_model": 5.0, | ||
| "batch_size": 256, | ||
| "buffer_size": 1000000, | ||
| "max_steps_exploration": 256, | ||
| "max_steps_training": 1000000, | ||
| "number_steps_per_train_policy": 1, | ||
|
|
||
| "reward_scale": 1.0, | ||
| "actor_lr": 3e-4, | ||
| "critic_lr": 3e-4, | ||
| "alpha_lr": 3e-4, | ||
| "gamma": 0.99, | ||
| "tau": 0.005, | ||
|
|
||
| "min_noise": 0.0, | ||
| "noise_scale": 0.1, | ||
| "noise_decay": 1.0, | ||
|
|
||
| "num_models": 6, | ||
| "num_rwd_models": 5, | ||
|
|
||
| "world_model_lr": 0.001, | ||
| "horizon": 3, | ||
| "sas": false, | ||
| "train_reward": true, | ||
| "train_both": false, | ||
| "gripper": false, | ||
| "threshold": 1.0, | ||
| "exploration_sample": 2 | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| { | ||
| "gym": "dmcs", | ||
| "task": "swingup", | ||
| "domain": "acrobot" | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| { | ||
| "seeds": [15,25,35,45,55], | ||
| "number_steps_per_evaluation": 10000, | ||
| "number_eval_episodes": 10 | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,33 @@ | ||
| { | ||
| "algorithm": "DynaSAC_Bounded_Yao", | ||
| "type": "mbrl", | ||
| "G": 1, | ||
| "G_model": 5.0, | ||
| "batch_size": 256, | ||
| "buffer_size": 1000000, | ||
| "max_steps_exploration": 256, | ||
| "max_steps_training": 1000000, | ||
| "number_steps_per_train_policy": 1, | ||
|
|
||
| "reward_scale": 1.0, | ||
| "actor_lr": 3e-4, | ||
| "critic_lr": 3e-4, | ||
| "alpha_lr": 3e-4, | ||
| "gamma": 0.99, | ||
| "tau": 0.005, | ||
|
|
||
| "min_noise": 0.0, | ||
| "noise_scale": 0.1, | ||
| "noise_decay": 1.0, | ||
|
|
||
| "num_models": 6, | ||
| "world_model_lr": 0.001, | ||
| "horizon": 1, | ||
| "num_samples": 10, | ||
| "sas": false, | ||
| "train_reward": true, | ||
| "train_both": false, | ||
| "gripper": false, | ||
| "threshold": 1.0, | ||
| "exploration_sample": 2 | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| { | ||
| "gym": "dmcs", | ||
| "task": "run", | ||
| "domain": "cheetah" | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| { | ||
| "seeds": [15, 25, 35, 45, 55], | ||
| "number_steps_per_evaluation": 10000, | ||
| "number_eval_episodes": 10 | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,34 @@ | ||
| { | ||
| "algorithm": "STEVESAC_Bounded_Yao", | ||
| "type": "mbrl", | ||
| "G": 1, | ||
| "G_model": 5.0, | ||
| "batch_size": 256, | ||
| "buffer_size": 1000000, | ||
| "max_steps_exploration": 256, | ||
| "max_steps_training": 1000000, | ||
| "number_steps_per_train_policy": 1, | ||
|
|
||
| "reward_scale": 1.0, | ||
| "actor_lr": 3e-4, | ||
| "critic_lr": 3e-4, | ||
| "alpha_lr": 3e-4, | ||
| "gamma": 0.99, | ||
| "tau": 0.005, | ||
|
|
||
| "min_noise": 0.0, | ||
| "noise_scale": 0.1, | ||
| "noise_decay": 1.0, | ||
|
|
||
| "num_models": 6, | ||
| "num_rwd_models": 5, | ||
|
|
||
| "world_model_lr": 0.001, | ||
| "horizon": 3, | ||
| "sas": false, | ||
| "train_reward": true, | ||
| "train_both": false, | ||
| "gripper": false, | ||
| "threshold": 1.0, | ||
| "exploration_sample": 2 | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| { | ||
| "gym": "dmcs", | ||
| "task": "run", | ||
| "domain": "cheetah" | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| { | ||
| "seeds": [15,25,35,45,55], | ||
| "number_steps_per_evaluation": 10000, | ||
| "number_eval_episodes": 10 | ||
| } |
33 changes: 33 additions & 0 deletions
33
env_finger_turn_hard/Dyna/DynaSAC_Bounded_Yao/alg_config.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,33 @@ | ||
| { | ||
| "algorithm": "DynaSAC_Bounded_Yao", | ||
| "type": "mbrl", | ||
| "G": 1, | ||
| "G_model": 5.0, | ||
| "batch_size": 256, | ||
| "buffer_size": 1000000, | ||
| "max_steps_exploration": 256, | ||
| "max_steps_training": 1000000, | ||
| "number_steps_per_train_policy": 1, | ||
|
|
||
| "reward_scale": 1.0, | ||
| "actor_lr": 3e-4, | ||
| "critic_lr": 3e-4, | ||
| "alpha_lr": 3e-4, | ||
| "gamma": 0.99, | ||
| "tau": 0.005, | ||
|
|
||
| "min_noise": 0.0, | ||
| "noise_scale": 0.1, | ||
| "noise_decay": 1.0, | ||
|
|
||
| "num_models": 6, | ||
| "world_model_lr": 0.001, | ||
| "horizon": 1, | ||
| "num_samples": 10, | ||
| "sas": false, | ||
| "train_reward": true, | ||
| "train_both": false, | ||
| "gripper": false, | ||
| "threshold": 1.0, | ||
| "exploration_sample": 2 | ||
| } |
5 changes: 5 additions & 0 deletions
5
env_finger_turn_hard/Dyna/DynaSAC_Bounded_Yao/env_config.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| { | ||
| "gym": "dmcs", | ||
| "task": "turn_hard", | ||
| "domain": "finger" | ||
| } |
5 changes: 5 additions & 0 deletions
5
env_finger_turn_hard/Dyna/DynaSAC_Bounded_Yao/train_config.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| { | ||
| "seeds": [15, 25, 35, 45, 55], | ||
| "number_steps_per_evaluation": 10000, | ||
| "number_eval_episodes": 10 | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,34 @@ | ||
| { | ||
| "algorithm": "STEVESAC_Bounded_Yao", | ||
| "type": "mbrl", | ||
| "G": 1, | ||
| "G_model": 5.0, | ||
| "batch_size": 256, | ||
| "buffer_size": 1000000, | ||
| "max_steps_exploration": 256, | ||
| "max_steps_training": 1000000, | ||
| "number_steps_per_train_policy": 1, | ||
|
|
||
| "reward_scale": 1.0, | ||
| "actor_lr": 3e-4, | ||
| "critic_lr": 3e-4, | ||
| "alpha_lr": 3e-4, | ||
| "gamma": 0.99, | ||
| "tau": 0.005, | ||
|
|
||
| "min_noise": 0.0, | ||
| "noise_scale": 0.1, | ||
| "noise_decay": 1.0, | ||
|
|
||
| "num_models": 6, | ||
| "num_rwd_models": 5, | ||
|
|
||
| "world_model_lr": 0.001, | ||
| "horizon": 3, | ||
| "sas": false, | ||
| "train_reward": true, | ||
| "train_both": false, | ||
| "gripper": false, | ||
| "threshold": 1.0, | ||
| "exploration_sample": 2 | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| { | ||
| "gym": "dmcs", | ||
| "task": "turn_hard", | ||
| "domain": "finger" | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| { | ||
| "seeds": [15,25,35,45,55], | ||
| "number_steps_per_evaluation": 10000, | ||
| "number_eval_episodes": 10 | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,33 @@ | ||
| { | ||
| "algorithm": "DynaSAC_Bounded_Yao", | ||
| "type": "mbrl", | ||
| "G": 1, | ||
| "G_model": 5.0, | ||
| "batch_size": 256, | ||
| "buffer_size": 1000000, | ||
| "max_steps_exploration": 256, | ||
| "max_steps_training": 1000000, | ||
| "number_steps_per_train_policy": 1, | ||
|
|
||
| "reward_scale": 1.0, | ||
| "actor_lr": 3e-4, | ||
| "critic_lr": 3e-4, | ||
| "alpha_lr": 3e-4, | ||
| "gamma": 0.99, | ||
| "tau": 0.005, | ||
|
|
||
| "min_noise": 0.0, | ||
| "noise_scale": 0.1, | ||
| "noise_decay": 1.0, | ||
|
|
||
| "num_models": 6, | ||
| "world_model_lr": 0.001, | ||
| "horizon": 1, | ||
| "num_samples": 10, | ||
| "sas": false, | ||
| "train_reward": true, | ||
| "train_both": false, | ||
| "gripper": false, | ||
| "threshold": 1.0, | ||
| "exploration_sample": 2 | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| { | ||
| "gym": "dmcs", | ||
| "task": "swim", | ||
| "domain": "fish" | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| { | ||
| "seeds": [15, 25, 35, 45, 55], | ||
| "number_steps_per_evaluation": 10000, | ||
| "number_eval_episodes": 10 | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,34 @@ | ||
| { | ||
| "algorithm": "STEVESAC_Bounded_Yao", | ||
| "type": "mbrl", | ||
| "G": 1, | ||
| "G_model": 5.0, | ||
| "batch_size": 256, | ||
| "buffer_size": 1000000, | ||
| "max_steps_exploration": 256, | ||
| "max_steps_training": 1000000, | ||
| "number_steps_per_train_policy": 1, | ||
|
|
||
| "reward_scale": 1.0, | ||
| "actor_lr": 3e-4, | ||
| "critic_lr": 3e-4, | ||
| "alpha_lr": 3e-4, | ||
| "gamma": 0.99, | ||
| "tau": 0.005, | ||
|
|
||
| "min_noise": 0.0, | ||
| "noise_scale": 0.1, | ||
| "noise_decay": 1.0, | ||
|
|
||
| "num_models": 6, | ||
| "num_rwd_models": 5, | ||
|
|
||
| "world_model_lr": 0.001, | ||
| "horizon": 3, | ||
| "sas": false, | ||
| "train_reward": true, | ||
| "train_both": false, | ||
| "gripper": false, | ||
| "threshold": 1.0, | ||
| "exploration_sample": 2 | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| { | ||
| "gym": "dmcs", | ||
| "task": "swim", | ||
| "domain": "fish" | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| { | ||
| "seeds": [15,25,35,45,55], | ||
| "number_steps_per_evaluation": 10000, | ||
| "number_eval_episodes": 10 | ||
| } |
Oops, something went wrong.