Initial commit

README.md

@@ -8,16 +8,17 @@ tags:
 model-index:
 - name: PPO
   results:
-  - metrics:
-    - type: mean_reward
-      value: -123.10 +/- 25.47
-      name: mean_reward
-    task:
+  - task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
       name: seals/MountainCar-v0
       type: seals/MountainCar-v0
+    metrics:
+    - type: mean_reward
+      value: -97.00 +/- 8.26
+      name: mean_reward
+      verified: false
 ---
 
 # **PPO** Agent playing **seals/MountainCar-v0**
@@ -35,21 +36,26 @@ RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
 SB3: https://github.com/DLR-RM/stable-baselines3<br/>
 SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
 
+Install the RL Zoo (with SB3 and SB3-Contrib):
+```bash
+pip install rl_zoo3
+```
+
 ```
 # Download model and save it into the logs/ folder
 python -m rl_zoo3.load_from_hub --algo ppo --env seals/MountainCar-v0 -orga HumanCompatibleAI -f logs/
-python enjoy.py --algo ppo --env seals/MountainCar-v0  -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env seals/MountainCar-v0  -f logs/
 ```
 
 If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
 ```
 python -m rl_zoo3.load_from_hub --algo ppo --env seals/MountainCar-v0 -orga HumanCompatibleAI -f logs/
-rl_zoo3 enjoy --algo ppo --env seals/MountainCar-v0  -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env seals/MountainCar-v0  -f logs/
 ```
 
 ## Training (with the RL Zoo)
 ```
-python train.py --algo ppo --env seals/MountainCar-v0 -f logs/
+python -m rl_zoo3.train --algo ppo --env seals/MountainCar-v0 -f logs/
 # Upload the model and generate video (when possible)
 python -m rl_zoo3.push_to_hub --algo ppo --env seals/MountainCar-v0 -f logs/ -orga HumanCompatibleAI
 ```
@@ -81,3 +87,8 @@ OrderedDict([('batch_size', 512),
                             'norm_reward': True},
                'norm_reward': False})])
 ```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

args.yml

@@ -10,7 +10,7 @@
   - - env_kwargs
     - null
   - - eval_episodes
-    - 5
+    - 0
   - - eval_freq
     - 25000
   - - gym_packages
@@ -18,7 +18,7 @@
   - - hyperparams
     - null
   - - log_folder
-    - logs
+    - gymnasium_models
   - - log_interval
     - -1
   - - max_total_trials
@@ -38,7 +38,7 @@
   - - no_optim_plots
     - false
   - - num_threads
-    - 1
+    - 4
   - - optimization_log_path
     - null
   - - optimize_hyperparameters
@@ -54,15 +54,15 @@
   - - save_replay_buffer
     - false
   - - seed
-    - 1
+    - 392828721
   - - storage
     - null
   - - study_name
     - null
   - - tensorboard_log
-    - runs/seals/MountainCar-v0__ppo__1__1672653886
+    - ''
   - - track
-    - true
+    - false
   - - trained_agent
     - ''
   - - truncate_last_trajectory
@@ -74,8 +74,8 @@
   - - verbose
     - 1
   - - wandb_entity
-    - ernestum
-  - - wandb_project_name
-    - seals-experts-normalized
-  - - yaml_file
     - null
+  - - wandb_project_name
+    - sb3
+  - - wandb_tags
+    - []

env_kwargs.yml

@@ -1 +1 @@
-{}
+render_mode: rgb_array

ppo-seals-MountainCar-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c8715d54c5150bcde97ff97bc982740c295aa3d64e4b06b9682e3a56ebba8db
-size 140740
+oid sha256:4a401c736574861304ae9f91f50e18071b68f7a385557fffd1a3e812a8efe00b
+size 138505

ppo-seals-MountainCar-v0/_stable_baselines3_version

@@ -1 +1 @@
-1.6.2
+2.2.0a3

ppo-seals-MountainCar-v0/data

@@ -3,77 +3,50 @@
         ":type:": "<class 'abc.ABCMeta'>",
         ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
         "__module__": "stable_baselines3.common.policies",
-        "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ",
-        "__init__": "<function ActorCriticPolicy.__init__ at 0x7faed9aed790>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7faed9aed820>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7faed9aed8b0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7faed9aed940>",
-        "_build": "<function ActorCriticPolicy._build at 0x7faed9aed9d0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7faed9aeda60>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7faed9aedaf0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7faed9aedb80>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7faed9aedc10>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7faed9aedca0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7faed9aedd30>",
+        "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f06f7a56ee0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f06f7a56f70>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f06f79db040>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f06f79db0d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f06f79db160>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f06f79db1f0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f06f79db280>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f06f79db310>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f06f79db3a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f06f79db430>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f06f79db4c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f06f79db550>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7faed9ae4c30>"
+        "_abc_impl": "<_abc_data object at 0x7f06f7a54d80>"
     },
     "verbose": 1,
     "policy_kwargs": {
         ":type:": "<class 'dict'>",
-        ":serialized:": "gAWVvAAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARUYW5olJOUjAhuZXRfYXJjaJRdlH2UKIwCcGmUXZQoS0BLQGWMAnZmlF2UKEtAS0BldWGMGGZlYXR1cmVzX2V4dHJhY3Rvcl9jbGFzc5SMF2ltaXRhdGlvbi5wb2xpY2llcy5iYXNllIwaTm9ybWFsaXplRmVhdHVyZXNFeHRyYWN0b3KUk5R1Lg==",
+        ":serialized:": "gAWVuQAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARUYW5olJOUjAhuZXRfYXJjaJR9lCiMAnBplF2UKEtAS0BljAJ2ZpRdlChLQEtAZXWMGGZlYXR1cmVzX2V4dHJhY3Rvcl9jbGFzc5SMF2ltaXRhdGlvbi5wb2xpY2llcy5iYXNllIwaTm9ybWFsaXplRmVhdHVyZXNFeHRyYWN0b3KUk5R1Lg==",
         "activation_fn": "<class 'torch.nn.modules.activation.Tanh'>",
-        "net_arch": [
-            {
-                "pi": [
-                    64,
-                    64
-                ],
-                "vf": [
-                    64,
-                    64
-                ]
-            }
-        ],
+        "net_arch": {
+            "pi": [
+                64,
+                64
+            ],
+            "vf": [
+                64,
+                64
+            ]
+        },
         "features_extractor_class": "<class 'imitation.policies.base.NormalizeFeaturesExtractor'>"
     },
-    "observation_space": {
-        ":type:": "<class 'gym.spaces.box.Box'>",
-        ":serialized:": "gAWVYwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAACamZm/KVyPvZRoCksChZSMAUOUdJRSlIwEaGlnaJRoEiiWCAAAAAAAAACamRk/KVyPPZRoCksChZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolgIAAAAAAAAAAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAoWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYCAAAAAAAAAAEBlGghSwKFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu",
-        "dtype": "float32",
-        "_shape": [
-            2
-        ],
-        "low": "[-1.2  -0.07]",
-        "high": "[0.6  0.07]",
-        "bounded_below": "[ True  True]",
-        "bounded_above": "[ True  True]",
-        "_np_random": null
-    },
-    "action_space": {
-        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
-        ":serialized:": "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",
-        "n": 3,
-        "_shape": [],
-        "dtype": "int64",
-        "_np_random": "RandomState(MT19937)"
-    },
-    "n_envs": 1,
     "num_timesteps": 1003520,
     "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
-    "seed": 4,
+    "seed": 0,
     "action_noise": null,
-    "start_time": 1672653888502052346,
+    "start_time": 1694771152324454564,
     "learning_rate": {
         ":type:": "<class 'function'>",
-        ":serialized:": "gAWVhQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMUy9ob21lL21heGltaWxpYW4vdmVudi9saWIvcHl0aG9uMy44L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flGgMdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoHn2UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHPz1Vp+meSZSFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
-    },
-    "tensorboard_log": "runs/seals/MountainCar-v0__ppo__1__1672653886/seals-MountainCar-v0",
-    "lr_schedule": {
-        ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWVlwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMZS9ob21lL21heGltaWxpYW4vcmwtYmFzZWxpbmVzMy16b28vdmVudi9saWIvcHl0aG9uMy44L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLg0MCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flGgMdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoHn2UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHPz1Vp+meSZSFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
     },
+    "tensorboard_log": null,
     "_last_obs": null,
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -81,21 +54,47 @@
     },
     "_last_original_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAPKF4L4AAAAArHrcvgAAAADko+i+AAAAAB7z5b4AAAAAyykTvwAAAADv6Ae/AAAAACWCC78AAAAAWPLvvgAAAACS0gK/AAAAAGl+9r4AAAAAYqkAvwAAAAALSQS/AAAAANWE7b4AAAAAo+gTvwAAAABIX9++AAAAAE8Pzr4AAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAHyIFb8AAAAAANsRvwAAAAAMG92+AAAAAAfI4r4AAAAAqWLhvgAAAAB2KRa/AAAAAGsdDL8AAAAAVwjavgAAAABhC/m+AAAAANRiCr8AAAAAqJ4QvwAAAADaLAi/AAAAAKofB78AAAAAxmMPvwAAAAA0Jem+AAAAAFRmCL8AAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="
     },
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
     "_current_progress_remaining": -0.0035199999999999676,
+    "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwFmAAAAAAACMAWyUS8iMAXSUR0Bz3njPv8ZUdX2UKGgGR8BaQAAAAAAAaAdLyGgIR0Bz3nUG3WnTdX2UKGgGR8BYAAAAAAAAaAdLyGgIR0Bz3nDP4VRDdX2UKGgGR8BaAAAAAAAAaAdLyGgIR0Bz3mq5sj3VdX2UKGgGR8BaQAAAAAAAaAdLyGgIR0Bz78+9rXUZdX2UKGgGR8BaAAAAAAAAaAdLyGgIR0Bz78mplz2fdX2UKGgGR8BaAAAAAAAAaAdLyGgIR0Bz78WP91lodX2UKGgGR8BZwAAAAAAAaAdLyGgIR0Bz78GcFyJbdX2UKGgGR8BYAAAAAAAAaAdLyGgIR0Bz771wo9cKdX2UKGgGR8BYQAAAAAAAaAdLyGgIR0Bz77mdRR/FdX2UKGgGR8BZwAAAAAAAaAdLyGgIR0Bz77WOIZZTdX2UKGgGR8BVQAAAAAAAaAdLyGgIR0Bz77GrCFbndX2UKGgGR8BZQAAAAAAAaAdLyGgIR0Bz763F1jiGdX2UKGgGR8BZQAAAAAAAaAdLyGgIR0Bz76n1nM+vdX2UKGgGR8BaQAAAAAAAaAdLyGgIR0Bz76YeDFqBdX2UKGgGR8BaAAAAAAAAaAdLyGgIR0Bz76HnEETydX2UKGgGR8BZgAAAAAAAaAdLyGgIR0Bz752IO6NEdX2UKGgGR8BZwAAAAAAAaAdLyGgIR0Bz75m4AjptdX2UKGgGR8BaAAAAAAAAaAdLyGgIR0Bz75WGRFI/dX2UKGgGR8BYwAAAAAAAaAdLyGgIR0Bz749wFTvRdX2UKGgGR8BVAAAAAAAAaAdLyGgIR0B0AKSV4X41dX2UKGgGR8BVQAAAAAAAaAdLyGgIR0B0AJ6NVBD5dX2UKGgGR8BZQAAAAAAAaAdLyGgIR0B0AJpztCzDdX2UKGgGR8BZwAAAAAAAaAdLyGgIR0B0AJaA4GUwdX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0AJJXhfjTdX2UKGgGR8BaQAAAAAAAaAdLyGgIR0B0AI6EJ0GNdX2UKGgGR8BaQAAAAAAAaAdLyGgIR0B0AIpz90ihdX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0AIaQ3gk1dX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0AIKrq+rVdX2UKGgGR8BZgAAAAAAAaAdLyGgIR0B0AH7di2DydX2UKGgGR8BZQAAAAAAAaAdLyGgIR0B0AHsKLKmsdX2UKGgGR8BZgAAAAAAAaAdLyGgIR0B0AHbTMJQddX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0AHJ2dNFjdX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0AG6g/TsqdX2UKGgGR8BVgAAAAAAAaAdLyGgIR0B0AGpm29csdX2UKGgGR8BYwAAAAAAAaAdLyGgIR0B0AGROk+HKdX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0EvIyTINmdX2UKGgGR8BaQAAAAAAAaAdLyGgIR0B0EuxY7q6fdX2UKGgGR8BZwAAAAAAAaAdLyGgIR0B0EuhysCDFdX2UKGgGR8BaQAAAAAAAaAdLyGgIR0B0EuSwGGEgdX2UKGgGR8BaQAAAAAAAaAdLyGgIR0B0EuCtihFmdX2UKGgGR8BZwAAAAAAAaAdLyGgIR0B0Et0U47zTdX2UKGgGR8BZwAAAAAAAaAdLyGgIR0B0Etkwvg3tdX2UKGgGR8BagAAAAAAAaAdLyGgIR0B0EtWKdhAodX2UKGgGR8BZwAAAAAAAaAdLyGgIR0B0EtG/etSydX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0Es4MnZ00dX2UKGgGR8BVgAAAAAAAaAdLyGgIR0B0EspazNUwdX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0EsZFXq7idX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0EsIHC4z8dX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0Er5P/JeWdX2UKGgGR8BXQAAAAAAAaAdLyGgIR0B0Ero4dZJTdX2UKGgGR8BZwAAAAAAAaAdLyGgIR0B0ErRCx/utdX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0F8hTwUg0dX2UKGgGR8BZgAAAAAAAaAdLyGgIR0B0F8JMQEpzdX2UKGgGR8BVAAAAAAAAaAdLyGgIR0B0F74593KTdX2UKGgGR8BZgAAAAAAAaAdLyGgIR0B0F7pIMBp6dX2UKGgGR8BZgAAAAAAAaAdLyGgIR0B0F7YcvM8pdX2UKGgGR8BWgAAAAAAAaAdLyGgIR0B0F7JW/8EWdX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0F65Gz8gqdX2UKGgGR8BXQAAAAAAAaAdLyGgIR0B0F6pzcRDkdX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0F6aPS2H+dX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0F6K/EfkndX2UKGgGR8Bi4AAAAAAAaAdLyGgIR0B0F57qptJndX2UKGgGR8BZgAAAAAAAaAdLyGgIR0B0F5qzqrzYdX2UKGgGR8BWQAAAAAAAaAdLyGgIR0B0F5ZV4oqkdX2UKGgGR8BWwAAAAAAAaAdLyGgIR0B0F5J/XoTxdX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0F45EMLF5dX2UKGgGR8BaQAAAAAAAaAdLyGgIR0B0F4guAZsLdX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0KHonrpqzdX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0KHQQcxTLdX2UKGgGR8BaQAAAAAAAaAdLyGgIR0B0KG/20zCUdX2UKGgGR8BXQAAAAAAAaAdLyGgIR0B0KGwQlKK6dX2UKGgGR8BZwAAAAAAAaAdLyGgIR0B0KGfra/RFdX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0KGQaJhvzdX2UKGgGR8BWgAAAAAAAaAdLyGgIR0B0KGAOJ+DwdX2UKGgGR8BaQAAAAAAAaAdLyGgIR0B0KFwtJ4B4dX2UKGgGR8BVQAAAAAAAaAdLyGgIR0B0KFhJAdGRdX2UKGgGR8BZwAAAAAAAaAdLyGgIR0B0KFR+BpYcdX2UKGgGR8BaQAAAAAAAaAdLyGgIR0B0KFCqp97XdX2UKGgGR8BaQAAAAAAAaAdLyGgIR0B0KEx1xKg7dX2UKGgGR8BVQAAAAAAAaAdLyGgIR0B0KEgaFVT8dX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0KERGtp22dX2UKGgGR8BagAAAAAAAaAdLyGgIR0B0KEANoakzdX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0KDn/1g6VdX2UKGgGR8BaQAAAAAAAaAdLyGgIR0B0Q1/rjYI0dX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0Q1nZkCmudX2UKGgGR8BaQAAAAAAAaAdLyGgIR0B0Q1W+49X+dX2UKGgGR8BVgAAAAAAAaAdLyGgIR0B0Q1HOKO1fdX2UKGgGR8BcQAAAAAAAaAdLyGgIR0B0Q02l2vB8dX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0Q0nSfDk3dX2UKGgGR8BaQAAAAAAAaAdLyGgIR0B0Q0XCTEBKdX2UKGgGR8BaQAAAAAAAaAdLyGgIR0B0Q0HfMwDedX2UKGgGR8BaQAAAAAAAaAdLyGgIR0B0Qz349HMEdX2UKGgGR8BVAAAAAAAAaAdLyGgIR0B0Qzopx3mndX2UKGgGR8BZwAAAAAAAaAdLyGgIR0B0QzZTQ3PzdX2UKGgGR8BVwAAAAAAAaAdLyGgIR0B0QzIcR15jdX2UKGgGR8BaAAAAAAAAaAdLyGgIR0B0Qy2+fywwdX2UKGgGR8BaQAAAAAAAaAdLyGgIR0B0Qynn+yZ8dX2UKGgGR8BZwAAAAAAAaAdLyGgIR0B0QyWszVMFdX2UKGgGR8BVQAAAAAAAaAdLyGgIR0B0Qx+XqqwRdWUu"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
     "_n_updates": 4900,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_shape": [
+            2
+        ],
+        "low": "[-1.2  -0.07]",
+        "high": "[0.6  0.07]",
+        "low_repr": "[-1.2  -0.07]",
+        "high_repr": "[0.6  0.07]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "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",
+        "n": "3",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
     "n_steps": 256,
     "gamma": 0.99,
     "gae_lambda": 0.98,
@@ -106,9 +105,13 @@
     "n_epochs": 20,
     "clip_range": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "clip_range_vf": null,
     "normalize_advantage": true,
-    "target_kl": null
+    "target_kl": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWVlwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMZS9ob21lL21heGltaWxpYW4vcmwtYmFzZWxpbmVzMy16b28vdmVudi9saWIvcHl0aG9uMy44L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLg0MCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flGgMdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoHn2UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHPz1Vp+meSZSFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
+    }
 }

ppo-seals-MountainCar-v0/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d37d94b78301e5971ad05c3a5a012d6519a32e0fb8250eb425a9d01e06145e45
+oid sha256:fe1c31ec7330c2541c0a041c35dbb6fabeaf54167bbb12708858af3318b003d8
 size 80889

ppo-seals-MountainCar-v0/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec8b2e9cc43bb7d40aae3cb3c2038dd7706e4167c592da2dead776535b2ad991
-size 40760
+oid sha256:db04f92e352505178fbc6e573fe383593c3755cbf7097e4ad8672c4c4e3ee434
+size 41528

ppo-seals-MountainCar-v0/system_info.txt

@@ -1,7 +1,9 @@
-OS: Linux-5.4.0-125-generic-x86_64-with-glibc2.29 #141-Ubuntu SMP Wed Aug 10 13:42:03 UTC 2022
-Python: 3.8.10
-Stable-Baselines3: 1.6.2
-PyTorch: 1.11.0+cu102
-GPU Enabled: False
-Numpy: 1.22.3
-Gym: 0.21.0
+- OS: Linux-5.4.0-156-generic-x86_64-with-glibc2.29 # 173-Ubuntu SMP Tue Jul 11 07:25:22 UTC 2023
+- Python: 3.8.10
+- Stable-Baselines3: 2.2.0a3
+- PyTorch: 2.0.1+cu117
+- GPU Enabled: False
+- Numpy: 1.24.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.21.0

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7097a70af23f56753ff4df18b7f212fdf859e8752a93846482e5612ca1c5146f
-size 176520
+oid sha256:5dfcea509de7c1b1323b96d2ba6e68ebe8f5924892b90b54aa65ce49f7756dc4
+size 143835

results.json

@@ -1 +1 @@
-{"mean_reward": -123.1, "std_reward": 25.469393396781165, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-02T11:15:35.759802"}
+{"mean_reward": -97.0, "std_reward": 8.258329128825032, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-19T11:40:45.961331"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11a94a0f3d92cc83a61ceb6f582f592dcf8c50a0b55aef0d6d4d6d374381341e
-size 119305
+oid sha256:cdeb0e756f12a772c492c7bc0011bd8abb8b0fbbd94a6e3c36325e3476aa845b
+size 114460

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17b0e58a05e432df8b67646a4caaf35e57a93ff193b4023911c74e0b141364ef
-size 3961
+oid sha256:8e4959055afcb1760e6aa9d920b0072e201a1e15a32224107646b72f89a68289
+size 1698