diff --git a/env_acrobot_swingup/Dyna/DynaSAC_Bounded_Yao/alg_config.json b/env_acrobot_swingup/Dyna/DynaSAC_Bounded_Yao/alg_config.json
new file mode 100644
index 0000000..9b38eaf
--- /dev/null
+++ b/env_acrobot_swingup/Dyna/DynaSAC_Bounded_Yao/alg_config.json
@@ -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
+}
\ No newline at end of file
diff --git a/env_acrobot_swingup/Dyna/DynaSAC_Bounded_Yao/env_config.json b/env_acrobot_swingup/Dyna/DynaSAC_Bounded_Yao/env_config.json
new file mode 100644
index 0000000..ce60721
--- /dev/null
+++ b/env_acrobot_swingup/Dyna/DynaSAC_Bounded_Yao/env_config.json
@@ -0,0 +1,5 @@
+{
+    "gym": "dmcs",
+    "task": "swingup",
+    "domain": "acrobot"
+}
diff --git a/env_acrobot_swingup/Dyna/DynaSAC_Bounded_Yao/train_config.json b/env_acrobot_swingup/Dyna/DynaSAC_Bounded_Yao/train_config.json
new file mode 100644
index 0000000..b1a5fa8
--- /dev/null
+++ b/env_acrobot_swingup/Dyna/DynaSAC_Bounded_Yao/train_config.json
@@ -0,0 +1,5 @@
+{
+    "seeds": [15, 25, 35, 45, 55],
+    "number_steps_per_evaluation": 10000,
+    "number_eval_episodes": 10
+}
diff --git a/env_acrobot_swingup/STEVE/STEVESAC_3_Yao/alg_config.json b/env_acrobot_swingup/STEVE/STEVESAC_3_Yao/alg_config.json
new file mode 100644
index 0000000..1e79453
--- /dev/null
+++ b/env_acrobot_swingup/STEVE/STEVESAC_3_Yao/alg_config.json
@@ -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
+}
\ No newline at end of file
diff --git a/env_acrobot_swingup/STEVE/STEVESAC_3_Yao/env_config.json b/env_acrobot_swingup/STEVE/STEVESAC_3_Yao/env_config.json
new file mode 100644
index 0000000..ce60721
--- /dev/null
+++ b/env_acrobot_swingup/STEVE/STEVESAC_3_Yao/env_config.json
@@ -0,0 +1,5 @@
+{
+    "gym": "dmcs",
+    "task": "swingup",
+    "domain": "acrobot"
+}
diff --git a/env_acrobot_swingup/STEVE/STEVESAC_3_Yao/train_config.json b/env_acrobot_swingup/STEVE/STEVESAC_3_Yao/train_config.json
new file mode 100644
index 0000000..07ba116
--- /dev/null
+++ b/env_acrobot_swingup/STEVE/STEVESAC_3_Yao/train_config.json
@@ -0,0 +1,5 @@
+{
+    "seeds": [15,25,35,45,55],
+    "number_steps_per_evaluation": 10000,
+    "number_eval_episodes": 10
+}
diff --git a/env_cheetah_run/Dyna/DynaSAC_Bounded_Yao/alg_config.json b/env_cheetah_run/Dyna/DynaSAC_Bounded_Yao/alg_config.json
new file mode 100644
index 0000000..9b38eaf
--- /dev/null
+++ b/env_cheetah_run/Dyna/DynaSAC_Bounded_Yao/alg_config.json
@@ -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
+}
\ No newline at end of file
diff --git a/env_cheetah_run/Dyna/DynaSAC_Bounded_Yao/env_config.json b/env_cheetah_run/Dyna/DynaSAC_Bounded_Yao/env_config.json
new file mode 100644
index 0000000..8cc0414
--- /dev/null
+++ b/env_cheetah_run/Dyna/DynaSAC_Bounded_Yao/env_config.json
@@ -0,0 +1,5 @@
+{
+    "gym": "dmcs",
+    "task": "run",
+    "domain": "cheetah"
+}
diff --git a/env_cheetah_run/Dyna/DynaSAC_Bounded_Yao/train_config.json b/env_cheetah_run/Dyna/DynaSAC_Bounded_Yao/train_config.json
new file mode 100644
index 0000000..b1a5fa8
--- /dev/null
+++ b/env_cheetah_run/Dyna/DynaSAC_Bounded_Yao/train_config.json
@@ -0,0 +1,5 @@
+{
+    "seeds": [15, 25, 35, 45, 55],
+    "number_steps_per_evaluation": 10000,
+    "number_eval_episodes": 10
+}
diff --git a/env_cheetah_run/STEVE/STEVESAC_3_Yao/alg_config.json b/env_cheetah_run/STEVE/STEVESAC_3_Yao/alg_config.json
new file mode 100644
index 0000000..1e79453
--- /dev/null
+++ b/env_cheetah_run/STEVE/STEVESAC_3_Yao/alg_config.json
@@ -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
+}
\ No newline at end of file
diff --git a/env_cheetah_run/STEVE/STEVESAC_3_Yao/env_config.json b/env_cheetah_run/STEVE/STEVESAC_3_Yao/env_config.json
new file mode 100644
index 0000000..8cc0414
--- /dev/null
+++ b/env_cheetah_run/STEVE/STEVESAC_3_Yao/env_config.json
@@ -0,0 +1,5 @@
+{
+    "gym": "dmcs",
+    "task": "run",
+    "domain": "cheetah"
+}
diff --git a/env_cheetah_run/STEVE/STEVESAC_3_Yao/train_config.json b/env_cheetah_run/STEVE/STEVESAC_3_Yao/train_config.json
new file mode 100644
index 0000000..07ba116
--- /dev/null
+++ b/env_cheetah_run/STEVE/STEVESAC_3_Yao/train_config.json
@@ -0,0 +1,5 @@
+{
+    "seeds": [15,25,35,45,55],
+    "number_steps_per_evaluation": 10000,
+    "number_eval_episodes": 10
+}
diff --git a/env_finger_turn_hard/Dyna/DynaSAC_Bounded_Yao/alg_config.json b/env_finger_turn_hard/Dyna/DynaSAC_Bounded_Yao/alg_config.json
new file mode 100644
index 0000000..9b38eaf
--- /dev/null
+++ b/env_finger_turn_hard/Dyna/DynaSAC_Bounded_Yao/alg_config.json
@@ -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
+}
\ No newline at end of file
diff --git a/env_finger_turn_hard/Dyna/DynaSAC_Bounded_Yao/env_config.json b/env_finger_turn_hard/Dyna/DynaSAC_Bounded_Yao/env_config.json
new file mode 100644
index 0000000..619b54b
--- /dev/null
+++ b/env_finger_turn_hard/Dyna/DynaSAC_Bounded_Yao/env_config.json
@@ -0,0 +1,5 @@
+{
+    "gym": "dmcs",
+    "task": "turn_hard",
+    "domain": "finger"
+}
diff --git a/env_finger_turn_hard/Dyna/DynaSAC_Bounded_Yao/train_config.json b/env_finger_turn_hard/Dyna/DynaSAC_Bounded_Yao/train_config.json
new file mode 100644
index 0000000..b1a5fa8
--- /dev/null
+++ b/env_finger_turn_hard/Dyna/DynaSAC_Bounded_Yao/train_config.json
@@ -0,0 +1,5 @@
+{
+    "seeds": [15, 25, 35, 45, 55],
+    "number_steps_per_evaluation": 10000,
+    "number_eval_episodes": 10
+}
diff --git a/env_finger_turn_hard/STEVE/STEVESAC_3_Yao/alg_config.json b/env_finger_turn_hard/STEVE/STEVESAC_3_Yao/alg_config.json
new file mode 100644
index 0000000..1e79453
--- /dev/null
+++ b/env_finger_turn_hard/STEVE/STEVESAC_3_Yao/alg_config.json
@@ -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
+}
\ No newline at end of file
diff --git a/env_finger_turn_hard/STEVE/STEVESAC_3_Yao/env_config.json b/env_finger_turn_hard/STEVE/STEVESAC_3_Yao/env_config.json
new file mode 100644
index 0000000..619b54b
--- /dev/null
+++ b/env_finger_turn_hard/STEVE/STEVESAC_3_Yao/env_config.json
@@ -0,0 +1,5 @@
+{
+    "gym": "dmcs",
+    "task": "turn_hard",
+    "domain": "finger"
+}
diff --git a/env_finger_turn_hard/STEVE/STEVESAC_3_Yao/train_config.json b/env_finger_turn_hard/STEVE/STEVESAC_3_Yao/train_config.json
new file mode 100644
index 0000000..07ba116
--- /dev/null
+++ b/env_finger_turn_hard/STEVE/STEVESAC_3_Yao/train_config.json
@@ -0,0 +1,5 @@
+{
+    "seeds": [15,25,35,45,55],
+    "number_steps_per_evaluation": 10000,
+    "number_eval_episodes": 10
+}
diff --git a/env_fish_swim/Dyna/DynaSAC_Bounded_Yao/alg_config.json b/env_fish_swim/Dyna/DynaSAC_Bounded_Yao/alg_config.json
new file mode 100644
index 0000000..9b38eaf
--- /dev/null
+++ b/env_fish_swim/Dyna/DynaSAC_Bounded_Yao/alg_config.json
@@ -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
+}
\ No newline at end of file
diff --git a/env_fish_swim/Dyna/DynaSAC_Bounded_Yao/env_config.json b/env_fish_swim/Dyna/DynaSAC_Bounded_Yao/env_config.json
new file mode 100644
index 0000000..9e6a7f9
--- /dev/null
+++ b/env_fish_swim/Dyna/DynaSAC_Bounded_Yao/env_config.json
@@ -0,0 +1,5 @@
+{
+    "gym": "dmcs",
+    "task": "swim",
+    "domain": "fish"
+}
diff --git a/env_fish_swim/Dyna/DynaSAC_Bounded_Yao/train_config.json b/env_fish_swim/Dyna/DynaSAC_Bounded_Yao/train_config.json
new file mode 100644
index 0000000..b1a5fa8
--- /dev/null
+++ b/env_fish_swim/Dyna/DynaSAC_Bounded_Yao/train_config.json
@@ -0,0 +1,5 @@
+{
+    "seeds": [15, 25, 35, 45, 55],
+    "number_steps_per_evaluation": 10000,
+    "number_eval_episodes": 10
+}
diff --git a/env_fish_swim/STEVE/STEVESAC_3_Yao/alg_config.json b/env_fish_swim/STEVE/STEVESAC_3_Yao/alg_config.json
new file mode 100644
index 0000000..1e79453
--- /dev/null
+++ b/env_fish_swim/STEVE/STEVESAC_3_Yao/alg_config.json
@@ -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
+}
\ No newline at end of file
diff --git a/env_fish_swim/STEVE/STEVESAC_3_Yao/env_config.json b/env_fish_swim/STEVE/STEVESAC_3_Yao/env_config.json
new file mode 100644
index 0000000..9e6a7f9
--- /dev/null
+++ b/env_fish_swim/STEVE/STEVESAC_3_Yao/env_config.json
@@ -0,0 +1,5 @@
+{
+    "gym": "dmcs",
+    "task": "swim",
+    "domain": "fish"
+}
diff --git a/env_fish_swim/STEVE/STEVESAC_3_Yao/train_config.json b/env_fish_swim/STEVE/STEVESAC_3_Yao/train_config.json
new file mode 100644
index 0000000..07ba116
--- /dev/null
+++ b/env_fish_swim/STEVE/STEVESAC_3_Yao/train_config.json
@@ -0,0 +1,5 @@
+{
+    "seeds": [15,25,35,45,55],
+    "number_steps_per_evaluation": 10000,
+    "number_eval_episodes": 10
+}
diff --git a/env_hopper_hop/Dyna/DynaSAC_Bounded_Yao/alg_config.json b/env_hopper_hop/Dyna/DynaSAC_Bounded_Yao/alg_config.json
new file mode 100644
index 0000000..9b38eaf
--- /dev/null
+++ b/env_hopper_hop/Dyna/DynaSAC_Bounded_Yao/alg_config.json
@@ -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
+}
\ No newline at end of file
diff --git a/env_hopper_hop/Dyna/DynaSAC_Bounded_Yao/env_config.json b/env_hopper_hop/Dyna/DynaSAC_Bounded_Yao/env_config.json
new file mode 100644
index 0000000..d1c47ad
--- /dev/null
+++ b/env_hopper_hop/Dyna/DynaSAC_Bounded_Yao/env_config.json
@@ -0,0 +1,5 @@
+{
+    "gym": "dmcs",
+    "task": "hop",
+    "domain": "hopper"
+}
diff --git a/env_hopper_hop/Dyna/DynaSAC_Bounded_Yao/train_config.json b/env_hopper_hop/Dyna/DynaSAC_Bounded_Yao/train_config.json
new file mode 100644
index 0000000..b1a5fa8
--- /dev/null
+++ b/env_hopper_hop/Dyna/DynaSAC_Bounded_Yao/train_config.json
@@ -0,0 +1,5 @@
+{
+    "seeds": [15, 25, 35, 45, 55],
+    "number_steps_per_evaluation": 10000,
+    "number_eval_episodes": 10
+}
diff --git a/env_hopper_hop/STEVE/STEVESAC_3_Yao/alg_config.json b/env_hopper_hop/STEVE/STEVESAC_3_Yao/alg_config.json
new file mode 100644
index 0000000..1e79453
--- /dev/null
+++ b/env_hopper_hop/STEVE/STEVESAC_3_Yao/alg_config.json
@@ -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
+}
\ No newline at end of file
diff --git a/env_hopper_hop/STEVE/STEVESAC_3_Yao/env_config.json b/env_hopper_hop/STEVE/STEVESAC_3_Yao/env_config.json
new file mode 100644
index 0000000..d1c47ad
--- /dev/null
+++ b/env_hopper_hop/STEVE/STEVESAC_3_Yao/env_config.json
@@ -0,0 +1,5 @@
+{
+    "gym": "dmcs",
+    "task": "hop",
+    "domain": "hopper"
+}
diff --git a/env_hopper_hop/STEVE/STEVESAC_3_Yao/train_config.json b/env_hopper_hop/STEVE/STEVESAC_3_Yao/train_config.json
new file mode 100644
index 0000000..07ba116
--- /dev/null
+++ b/env_hopper_hop/STEVE/STEVESAC_3_Yao/train_config.json
@@ -0,0 +1,5 @@
+{
+    "seeds": [15,25,35,45,55],
+    "number_steps_per_evaluation": 10000,
+    "number_eval_episodes": 10
+}
diff --git a/env_humanoid_run/Dyna/DynaSAC_Bounded_Yao/alg_config.json b/env_humanoid_run/Dyna/DynaSAC_Bounded_Yao/alg_config.json
new file mode 100644
index 0000000..9b38eaf
--- /dev/null
+++ b/env_humanoid_run/Dyna/DynaSAC_Bounded_Yao/alg_config.json
@@ -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
+}
\ No newline at end of file
diff --git a/env_humanoid_run/Dyna/DynaSAC_Bounded_Yao/env_config.json b/env_humanoid_run/Dyna/DynaSAC_Bounded_Yao/env_config.json
new file mode 100644
index 0000000..ef57631
--- /dev/null
+++ b/env_humanoid_run/Dyna/DynaSAC_Bounded_Yao/env_config.json
@@ -0,0 +1,5 @@
+{
+    "gym": "dmcs",
+    "task": "run",
+    "domain": "humanoid"
+}
diff --git a/env_humanoid_run/Dyna/DynaSAC_Bounded_Yao/train_config.json b/env_humanoid_run/Dyna/DynaSAC_Bounded_Yao/train_config.json
new file mode 100644
index 0000000..b1a5fa8
--- /dev/null
+++ b/env_humanoid_run/Dyna/DynaSAC_Bounded_Yao/train_config.json
@@ -0,0 +1,5 @@
+{
+    "seeds": [15, 25, 35, 45, 55],
+    "number_steps_per_evaluation": 10000,
+    "number_eval_episodes": 10
+}
diff --git a/env_humanoid_run/STEVE/STEVESAC_3_Yao/alg_config.json b/env_humanoid_run/STEVE/STEVESAC_3_Yao/alg_config.json
new file mode 100644
index 0000000..1e79453
--- /dev/null
+++ b/env_humanoid_run/STEVE/STEVESAC_3_Yao/alg_config.json
@@ -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
+}
\ No newline at end of file
diff --git a/env_humanoid_run/STEVE/STEVESAC_3_Yao/env_config.json b/env_humanoid_run/STEVE/STEVESAC_3_Yao/env_config.json
new file mode 100644
index 0000000..ef57631
--- /dev/null
+++ b/env_humanoid_run/STEVE/STEVESAC_3_Yao/env_config.json
@@ -0,0 +1,5 @@
+{
+    "gym": "dmcs",
+    "task": "run",
+    "domain": "humanoid"
+}
diff --git a/env_humanoid_run/STEVE/STEVESAC_3_Yao/train_config.json b/env_humanoid_run/STEVE/STEVESAC_3_Yao/train_config.json
new file mode 100644
index 0000000..07ba116
--- /dev/null
+++ b/env_humanoid_run/STEVE/STEVESAC_3_Yao/train_config.json
@@ -0,0 +1,5 @@
+{
+    "seeds": [15,25,35,45,55],
+    "number_steps_per_evaluation": 10000,
+    "number_eval_episodes": 10
+}
diff --git a/env_reacher_hard/Dyna/DynaSAC_Bounded_Yao/alg_config.json b/env_reacher_hard/Dyna/DynaSAC_Bounded_Yao/alg_config.json
new file mode 100644
index 0000000..e8a2b30
--- /dev/null
+++ b/env_reacher_hard/Dyna/DynaSAC_Bounded_Yao/alg_config.json
@@ -0,0 +1,33 @@
+{
+    "algorithm": "DynaSAC_Bounded_Yao",
+    "type": "mbrl",
+    "G": 1,
+    "G_model": 5.0,
+    "batch_size": 256,
+    "buffer_size": 400000,
+    "max_steps_exploration": 256,
+    "max_steps_training": 400000,
+    "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
+}
\ No newline at end of file
diff --git a/env_reacher_hard/Dyna/DynaSAC_Bounded_Yao/env_config.json b/env_reacher_hard/Dyna/DynaSAC_Bounded_Yao/env_config.json
new file mode 100644
index 0000000..64cc733
--- /dev/null
+++ b/env_reacher_hard/Dyna/DynaSAC_Bounded_Yao/env_config.json
@@ -0,0 +1,5 @@
+{
+    "gym": "dmcs",
+    "task": "hard",
+    "domain": "reacher"
+}
diff --git a/env_reacher_hard/Dyna/DynaSAC_Bounded_Yao/train_config.json b/env_reacher_hard/Dyna/DynaSAC_Bounded_Yao/train_config.json
new file mode 100644
index 0000000..b1a5fa8
--- /dev/null
+++ b/env_reacher_hard/Dyna/DynaSAC_Bounded_Yao/train_config.json
@@ -0,0 +1,5 @@
+{
+    "seeds": [15, 25, 35, 45, 55],
+    "number_steps_per_evaluation": 10000,
+    "number_eval_episodes": 10
+}
diff --git a/env_reacher_hard/STEVE/STEVESAC_3_Yao/alg_config.json b/env_reacher_hard/STEVE/STEVESAC_3_Yao/alg_config.json
new file mode 100644
index 0000000..ec00e52
--- /dev/null
+++ b/env_reacher_hard/STEVE/STEVESAC_3_Yao/alg_config.json
@@ -0,0 +1,34 @@
+{
+    "algorithm": "STEVESAC_Bounded_Yao",
+    "type": "mbrl",
+    "G": 1,
+    "G_model": 5.0,
+    "batch_size": 256,
+    "buffer_size": 400000,
+    "max_steps_exploration": 256,
+    "max_steps_training": 400000,
+    "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
+}
\ No newline at end of file
diff --git a/env_reacher_hard/STEVE/STEVESAC_3_Yao/env_config.json b/env_reacher_hard/STEVE/STEVESAC_3_Yao/env_config.json
new file mode 100644
index 0000000..64cc733
--- /dev/null
+++ b/env_reacher_hard/STEVE/STEVESAC_3_Yao/env_config.json
@@ -0,0 +1,5 @@
+{
+    "gym": "dmcs",
+    "task": "hard",
+    "domain": "reacher"
+}
diff --git a/env_reacher_hard/STEVE/STEVESAC_3_Yao/train_config.json b/env_reacher_hard/STEVE/STEVESAC_3_Yao/train_config.json
new file mode 100644
index 0000000..07ba116
--- /dev/null
+++ b/env_reacher_hard/STEVE/STEVESAC_3_Yao/train_config.json
@@ -0,0 +1,5 @@
+{
+    "seeds": [15,25,35,45,55],
+    "number_steps_per_evaluation": 10000,
+    "number_eval_episodes": 10
+}
diff --git a/env_walker_walk/Dyna/DynaSAC_Bounded_Yao/alg_config.json b/env_walker_walk/Dyna/DynaSAC_Bounded_Yao/alg_config.json
new file mode 100644
index 0000000..e8a2b30
--- /dev/null
+++ b/env_walker_walk/Dyna/DynaSAC_Bounded_Yao/alg_config.json
@@ -0,0 +1,33 @@
+{
+    "algorithm": "DynaSAC_Bounded_Yao",
+    "type": "mbrl",
+    "G": 1,
+    "G_model": 5.0,
+    "batch_size": 256,
+    "buffer_size": 400000,
+    "max_steps_exploration": 256,
+    "max_steps_training": 400000,
+    "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
+}
\ No newline at end of file
diff --git a/env_walker_walk/Dyna/DynaSAC_Bounded_Yao/env_config.json b/env_walker_walk/Dyna/DynaSAC_Bounded_Yao/env_config.json
new file mode 100644
index 0000000..3303c68
--- /dev/null
+++ b/env_walker_walk/Dyna/DynaSAC_Bounded_Yao/env_config.json
@@ -0,0 +1,5 @@
+{
+    "gym": "dmcs",
+    "task": "walk",
+    "domain": "walker"
+}
diff --git a/env_walker_walk/Dyna/DynaSAC_Bounded_Yao/train_config.json b/env_walker_walk/Dyna/DynaSAC_Bounded_Yao/train_config.json
new file mode 100644
index 0000000..b1a5fa8
--- /dev/null
+++ b/env_walker_walk/Dyna/DynaSAC_Bounded_Yao/train_config.json
@@ -0,0 +1,5 @@
+{
+    "seeds": [15, 25, 35, 45, 55],
+    "number_steps_per_evaluation": 10000,
+    "number_eval_episodes": 10
+}
diff --git a/env_walker_walk/STEVE/STEVESAC_3_Yao/alg_config.json b/env_walker_walk/STEVE/STEVESAC_3_Yao/alg_config.json
new file mode 100644
index 0000000..ec00e52
--- /dev/null
+++ b/env_walker_walk/STEVE/STEVESAC_3_Yao/alg_config.json
@@ -0,0 +1,34 @@
+{
+    "algorithm": "STEVESAC_Bounded_Yao",
+    "type": "mbrl",
+    "G": 1,
+    "G_model": 5.0,
+    "batch_size": 256,
+    "buffer_size": 400000,
+    "max_steps_exploration": 256,
+    "max_steps_training": 400000,
+    "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
+}
\ No newline at end of file
diff --git a/env_walker_walk/STEVE/STEVESAC_3_Yao/env_config.json b/env_walker_walk/STEVE/STEVESAC_3_Yao/env_config.json
new file mode 100644
index 0000000..3303c68
--- /dev/null
+++ b/env_walker_walk/STEVE/STEVESAC_3_Yao/env_config.json
@@ -0,0 +1,5 @@
+{
+    "gym": "dmcs",
+    "task": "walk",
+    "domain": "walker"
+}
diff --git a/env_walker_walk/STEVE/STEVESAC_3_Yao/train_config.json b/env_walker_walk/STEVE/STEVESAC_3_Yao/train_config.json
new file mode 100644
index 0000000..07ba116
--- /dev/null
+++ b/env_walker_walk/STEVE/STEVESAC_3_Yao/train_config.json
@@ -0,0 +1,5 @@
+{
+    "seeds": [15,25,35,45,55],
+    "number_steps_per_evaluation": 10000,
+    "number_eval_episodes": 10
+}
diff --git a/sample_iw/alg_config.json b/sample_iw/alg_config.json
new file mode 100644
index 0000000..d1c50aa
--- /dev/null
+++ b/sample_iw/alg_config.json
@@ -0,0 +1,33 @@
+{
+    "algorithm": "DynaSAC_NS_IW",
+    "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": 0.5
+}
\ No newline at end of file
diff --git a/sample_iw/env_config.json b/sample_iw/env_config.json
new file mode 100644
index 0000000..4d0e5d8
--- /dev/null
+++ b/sample_iw/env_config.json
@@ -0,0 +1,5 @@
+{
+    "gym": "dmcs",
+    "task": "catch",
+    "domain": "ball_in_cup"
+}
diff --git a/sample_iw/train_config.json b/sample_iw/train_config.json
new file mode 100644
index 0000000..b1a5fa8
--- /dev/null
+++ b/sample_iw/train_config.json
@@ -0,0 +1,5 @@
+{
+    "seeds": [15, 25, 35, 45, 55],
+    "number_steps_per_evaluation": 10000,
+    "number_eval_episodes": 10
+}