Initial commit

README.md

@@ -8,16 +8,17 @@ tags:
 model-index:
 - name: PPO
   results:
-  - metrics:
-    - type: mean_reward
-      value: 500.00 +/- 0.00
-      name: mean_reward
-    task:
+  - task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
       name: seals/CartPole-v0
       type: seals/CartPole-v0
+    metrics:
+    - type: mean_reward
+      value: 500.00 +/- 0.00
+      name: mean_reward
+      verified: false
 ---
 
 # **PPO** Agent playing **seals/CartPole-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/CartPole-v0 -orga HumanCompatibleAI -f logs/
-python enjoy.py --algo ppo --env seals/CartPole-v0  -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env seals/CartPole-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/CartPole-v0 -orga HumanCompatibleAI -f logs/
-rl_zoo3 enjoy --algo ppo --env seals/CartPole-v0  -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env seals/CartPole-v0  -f logs/
 ```
 
 ## Training (with the RL Zoo)
 ```
-python train.py --algo ppo --env seals/CartPole-v0 -f logs/
+python -m rl_zoo3.train --algo ppo --env seals/CartPole-v0 -f logs/
 # Upload the model and generate video (when possible)
 python -m rl_zoo3.push_to_hub --algo ppo --env seals/CartPole-v0 -f logs/ -orga HumanCompatibleAI
 ```
@@ -74,3 +80,8 @@ OrderedDict([('batch_size', 256),
              ('vf_coef', 0.489343896591493),
              ('normalize', 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
-    - 7
+    - 705888933
   - - storage
     - null
   - - study_name
     - null
   - - tensorboard_log
-    - runs/seals/CartPole-v0__ppo__7__1670516892
+    - ''
   - - 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-CartPole-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdd3c7bf2dd46d22c904d7e34142fcc7334a2600f415fa247e80e88ecc7c9376
-size 141656
+oid sha256:4e57a2618e1ab32ee4c5267874ae9f630896bc73991bd68392f5c78e4ecf738d
+size 139005

ppo-seals-CartPole-v0/_stable_baselines3_version

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

ppo-seals-CartPole-v0/data

@@ -3,76 +3,49 @@
         ":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 0x7fe4b5b38700>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fe4b5b38790>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fe4b5b38820>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fe4b5b388b0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7fe4b5b38940>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7fe4b5b389d0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fe4b5b38a60>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7fe4b5b38af0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fe4b5b38b80>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fe4b5b38c10>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fe4b5b38ca0>",
+        "__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 0x7fcc418e2ee0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcc418e2f70>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcc41867040>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcc418670d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fcc41867160>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fcc418671f0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fcc41867280>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcc41867310>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fcc418673a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcc41867430>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcc418674c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcc41867550>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7fe4b5b2fba0>"
+        "_abc_impl": "<_abc_data object at 0x7fcc418cdc90>"
     },
     "verbose": 1,
     "policy_kwargs": {
         ":type:": "<class 'dict'>",
-        ":serialized:": "gAWVaAAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARSZUxVlJOUjAhuZXRfYXJjaJRdlH2UKIwCcGmUXZQoS0BLQGWMAnZmlF2UKEtAS0BldWF1Lg==",
+        ":serialized:": "gAWVZQAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARSZUxVlJOUjAhuZXRfYXJjaJR9lCiMAnBplF2UKEtAS0BljAJ2ZpRdlChLQEtAZXV1Lg==",
         "activation_fn": "<class 'torch.nn.modules.activation.ReLU'>",
-        "net_arch": [
-            {
-                "pi": [
-                    64,
-                    64
-                ],
-                "vf": [
-                    64,
-                    64
-                ]
-            }
-        ]
+        "net_arch": {
+            "pi": [
+                64,
+                64
+            ],
+            "vf": [
+                64,
+                64
+            ]
+        }
     },
-    "observation_space": {
-        ":type:": "<class 'gym.spaces.box.Box'>",
-        ":serialized:": "gAWVdwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLBIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAD//3////9//9sPScD//3//lGgKSwSFlIwBQ5R0lFKUjARoaWdolGgSKJYQAAAAAAAAAP//f3///39/2w9JQP//f3+UaApLBIWUaBV0lFKUjA1ib3VuZGVkX2JlbG93lGgSKJYEAAAAAAAAAAEBAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLBIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYEAAAAAAAAAAEBAQGUaCFLBIWUaBV0lFKUjApfbnBfcmFuZG9tlE51Yi4=",
-        "dtype": "float32",
-        "_shape": [
-            4
-        ],
-        "low": "[-3.4028235e+38 -3.4028235e+38 -3.1415927e+00 -3.4028235e+38]",
-        "high": "[3.4028235e+38 3.4028235e+38 3.1415927e+00 3.4028235e+38]",
-        "bounded_below": "[ True  True  True  True]",
-        "bounded_above": "[ True  True  True  True]",
-        "_np_random": null
-    },
-    "action_space": {
-        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
-        ":serialized:": "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",
-        "n": 2,
-        "_shape": [],
-        "dtype": "int64",
-        "_np_random": "RandomState(MT19937)"
-    },
-    "n_envs": 1,
     "num_timesteps": 102400,
     "_total_timesteps": 100000,
     "_num_timesteps_at_start": 0,
-    "seed": 1,
+    "seed": 0,
     "action_noise": null,
-    "start_time": 1670516894814637504,
+    "start_time": 1694771152136710495,
     "learning_rate": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
-    },
-    "tensorboard_log": "runs/seals/CartPole-v0__ppo__7__1670516892/seals-CartPole-v0",
-    "lr_schedule": {
-        ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
+    "tensorboard_log": null,
     "_last_obs": null,
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -83,15 +56,41 @@
     "use_sde": false,
     "sde_sample_freq": -1,
     "_current_progress_remaining": -0.02400000000000002,
+    "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWVRAwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQH9AAAAAAACMAWyUTfQBjAF0lEdAKPgtFrl/6XV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQCj3yup0fYB1fZQoaAZHQH9AAAAAAABoB030AWgIR0Ao92h7E5yVdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAKPcEmplz2nV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQCpPgNwzch11fZQoaAZHQH9AAAAAAABoB030AWgIR0AqTxOtW+49dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAKk6vA44p+nV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQCpOSZBsyi51fZQoaAZHQH9AAAAAAABoB030AWgIR0AqTd+ocaOxdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAKk19v0h/zHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQCpNGy5Zr591fZQoaAZHQH9AAAAAAABoB030AWgIR0AqTLdvbXYldX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAK6eYMOPNmnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQCunPC2tuDV1fZQoaAZHQH9AAAAAAABoB030AWgIR0ArptjTa0x/dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAK6Z0bLlmvnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQCumC04R28t1fZQoaAZHQH9AAAAAAABoB030AWgIR0ArpaouPFNtdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAK6VIiC8OC3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQCuk5fdAPd51fZQoaAZHQH9AAAAAAABoB030AWgIR0As/5HmRvFWdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdALP8iwB5ooXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQCz+wmmce8x1fZQoaAZHQH9AAAAAAABoB030AWgIR0As/l2eQMhHdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdALP3zlLeyiXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQCz9kWhysCF1fZQoaAZHQH9AAAAAAABoB030AWgIR0As/S88La24dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdALPzLW7OE/XV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQC5VVNpM6BB1fZQoaAZHQH9AAAAAAABoB030AWgIR0AuVOgxrSE2dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdALlSDh99c8nV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQC5UHlfZ26l1fZQoaAZHQH9AAAAAAABoB030AWgIR0AuU7Rv3rUtdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdALlNSZSeiBXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQC5S7/XGwRp1fZQoaAZHQH9AAAAAAABoB030AWgIR0AuUox59mYjdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAL6s2FWXC0nV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQC+qxs2vStx1fZQoaAZHQH9AAAAAAABoB030AWgIR0AvqmG/N7jUdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAL6n8KohpxnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQC+pkf9xZMd1fZQoaAZHQH9AAAAAAABoB030AWgIR0AvqTAWSEDhdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAL6jNyHVPN3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQC+oam4y44J1fZQoaAZHQH9AAAAAAABoB030AWgIR0AwgK9PDYRNdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAMIB2B8QZoHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQDCAQ4CIUJx1fZQoaAZHQH9AAAAAAABoB030AWgIR0AwgBClabF1dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAMH/boKUmlnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQDB/qoqCpWF1fZQoaAZHQH9AAAAAAABoB030AWgIR0Awf3lS0jTsdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAMH9Hc1wYL3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQDEro7muDBd1fZQoaAZHQH9AAAAAAABoB030AWgIR0AxK2vjfek6dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAMSs5sCT2WnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQDErBwdbPhR1fZQoaAZHQH9AAAAAAABoB030AWgIR0AxKtITXarWdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAMSqhQFcIJXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQDEqcCo0hvB1fZQoaAZHQH9AAAAAAABoB030AWgIR0AxKj5sTFl1dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAMdd3W4EwFnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQDHXQAuIyj51fZQoaAZHQH9AAAAAAABoB030AWgIR0Ax1w2ETQE7dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAMdbayrxRVXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQDHWpaRp1zR1fZQoaAZHQH9AAAAAAABoB030AWgIR0Ax1nSv1UVBdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAMdZDeCTUzHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQDHWEZiuuA91fZQoaAZHQH9AAAAAAABoB030AWgIR0AyglwcYIjXdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAMoImLLpzLnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQDKB9Dx9XtB1fZQoaAZHQH9AAAAAAABoB030AWgIR0AygcGC7K7qdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAMoGMju8brHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQDKBW7voePt1fZQoaAZHQH9AAAAAAABoB030AWgIR0AygSqEOAiFdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAMoD5CWu5jHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQDMumTC+De11fZQoaAZHQH9AAAAAAABoB030AWgIR0AzLmYjSofkdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAMy40VJtix3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQDMuAc1fmcR1fZQoaAZHQH9AAAAAAABoB030AWgIR0AzLc3l0YCRdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAMy2dVea8YnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQDMtbHIZIhB1fZQoaAZHQH9AAAAAAABoB030AWgIR0AzLTrVvuPWdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAM9lVDKHO8nV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQDPZHz6JqIt1fZQoaAZHQH9AAAAAAABoB030AWgIR0Az2Oz6ab4KdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAM9i6QNkOJHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQDPYhTwUg0V1fZQoaAZHQH9AAAAAAABoB030AWgIR0Az2FRYRujzdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAM9gjUutfX3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQDPX8XN1QqJ1fZQoaAZHQH9AAAAAAABoB030AWgIR0A0g0xM36yjdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdANIMVHnU2DXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQDSC4qgAZKp1fZQoaAZHQH9AAAAAAABoB030AWgIR0A0gq/ub7TEdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdANIJ6+nIhhnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQDSCSr5qM3t1fZQoaAZHQH9AAAAAAABoB030AWgIR0A0ghl18stkdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdANIHnuAqd6XVlLg=="
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
     "_n_updates": 250,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True]",
+        "bounded_above": "[ True  True  True  True]",
+        "_shape": [
+            4
+        ],
+        "low": "[-3.4028235e+38 -3.4028235e+38 -3.1415927e+00 -3.4028235e+38]",
+        "high": "[3.4028235e+38 3.4028235e+38 3.1415927e+00 3.4028235e+38]",
+        "low_repr": "[-3.4028235e+38 -3.4028235e+38 -3.1415927e+00 -3.4028235e+38]",
+        "high_repr": "[3.4028235e+38 3.4028235e+38 3.1415927e+00 3.4028235e+38]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "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",
+        "n": "2",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
     "n_steps": 512,
     "gamma": 0.9999,
     "gae_lambda": 0.9,
@@ -102,9 +101,13 @@
     "n_epochs": 10,
     "clip_range": {
         ":type:": "<class 'function'>",
-        ":serialized:": "gAWVhQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMUy9ob21lL21heGltaWxpYW4vdmVudi9saWIvcHl0aG9uMy44L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flGgMdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoHn2UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP9mZmZmZmZqFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
+        ":serialized:": "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"
     },
     "clip_range_vf": null,
     "normalize_advantage": true,
-    "target_kl": null
+    "target_kl": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
 }

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f8f95042d63d71329a83889b244855b119ff1fde42470577638bb8a7472455e
+oid sha256:40da409386ebbb12b110342c54781f79f6bb75a7011b5c77349fc23803476222
 size 82425

ppo-seals-CartPole-v0/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:385b42f25c52b68029dd9c47cf3b1b779c3ec4a4441606218bacd6091fa5bb6f
-size 40513
+oid sha256:6db5d09a0139e686bcea8d28033d45282a219872cdf9615bd34f323321953549
+size 40641

ppo-seals-CartPole-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 sha256:4b7051380170d8c8c4a86101d6def7c0b8950e420b0bbd4775b96c1e170313aa
-size 60768
+oid sha256:dfb42af0cb0886d40c42ccbae54457ef7c113e14260731dfef78f395def361e0
+size 52504

results.json

@@ -1 +1 @@
-{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-29T14:39:42.298440"}
+{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-19T11:41:29.721520"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:913814bce3741222e544117345a87cf5fd970bd301ff0985679b10763887659e
-size 6702
+oid sha256:03f1d3442617ea155b2db3cfa07f3ddc9d43802819794da0b59f1af6f74b70b0
+size 6345