First working LunarLander-v2 model (base) with video

README.md

@@ -1,11 +1,10 @@
 ---
+library_name: stable-baselines3
 tags:
 - LunarLander-v2
-- ppo
 - deep-reinforcement-learning
 - reinforcement-learning
-- custom-implementation
-- deep-rl-course
+- stable-baselines3
 model-index:
 - name: PPO
   results:
@@ -17,45 +16,25 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -178.68 +/- 88.28
+      value: 237.31 +/- 19.26
       name: mean_reward
       verified: false
 ---
 
-  # PPO Agent Playing LunarLander-v2
-
-  This is a trained model of a PPO agent playing LunarLander-v2.
-
-  # Hyperparameters
-  ```python
-  {'exp_name': 'my_experiment'
-'seed': 1
-'torch_deterministic': True
-'cuda': True
-'track': False
-'wandb_project_name': 'cleanRL'
-'wandb_entity': None
-'capture_video': False
-'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
-'learning_rate': 2.5e-05
-'num_envs': 8
-'num_steps': 2048
-'anneal_lr': True
-'gae': True
-'gamma': 0.999
-'gae_lambda': 0.98
-'num_minibatches': 4
-'update_epochs': 4
-'norm_adv': True
-'clip_coef': 0.2
-'clip_vloss': True
-'ent_coef': 0.01
-'vf_coef': 0.5
-'max_grad_norm': 0.5
-'target_kl': None
-'repo_id': 'ThomasSimonini/ppo-CartPole-v1'
-'batch_size': 16384
-'minibatch_size': 4096}
-  ```
-  
+# **PPO** Agent playing **LunarLander-v2**
+
+This is a trained model of a **PPO** agent playing **LunarLander-v2**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+
+
+## Usage (with Stable-baselines3)
+
+TODO: Add your code
+
+
+```python
+from stable_baselines3 import ...
+from huggingface_sb3 import load_from_hub
+
+...
+```

config.json

@@ -1 +1 @@
-{"policy_class": {":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 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 0x7f0d132d6e60>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0d132d6ef0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0d132d6f80>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0d132d7010>", "_build": "<function ActorCriticPolicy._build at 0x7f0d132d70a0>", "forward": "<function ActorCriticPolicy.forward at 0x7f0d132d7130>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f0d132d71c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0d132d7250>", "_predict": "<function ActorCriticPolicy._predict at 0x7f0d132d72e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0d132d7370>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0d132d7400>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0d132d7490>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f0d132e1400>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1768386058603350124, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 124, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 2048, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.17.13-200.fc42.x86_64-x86_64-with-glibc2.41 # 1 SMP PREEMPT_DYNAMIC Thu Dec 18 22:18:24 UTC 2025", "Python": "3.10.19", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.9.1+cu128", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.2", "Gymnasium": "0.28.1"}}
+{"policy_class": {":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 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 0x7f853e17e050>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f853e17e0e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f853e17e170>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f853e17e200>", "_build": "<function ActorCriticPolicy._build at 0x7f853e17e290>", "forward": "<function ActorCriticPolicy.forward at 0x7f853e17e320>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f853e17e3b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f853e17e440>", "_predict": "<function ActorCriticPolicy._predict at 0x7f853e17e4d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f853e17e560>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f853e17e5f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f853e17e680>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f853e699580>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1768386058603350124, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 124, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVdgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 2048, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.18.9-100.fc42.x86_64-x86_64-with-glibc2.41 # 1 SMP PREEMPT_DYNAMIC Fri Feb  6 18:42:22 UTC 2026", "Python": "3.10.19", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.9.1+cu128", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.2", "Gymnasium": "0.28.1", "OpenAI Gym": "0.22.0"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31bb34222783b4a0ac3ec19596c1825673e4f63d4537549ea30751d40d705a0a
-size 148522
+oid sha256:db1363e49cf3136de5ccc8924924186d58d31e66cd143cc0de5aa548915afbfa
+size 148542

ppo-LunarLander-v2/data

@@ -4,20 +4,20 @@
         ":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 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 0x7f0d132d6e60>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0d132d6ef0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0d132d6f80>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0d132d7010>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f0d132d70a0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f0d132d7130>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f0d132d71c0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0d132d7250>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f0d132d72e0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0d132d7370>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0d132d7400>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0d132d7490>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f853e17e050>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f853e17e0e0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f853e17e170>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f853e17e200>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f853e17e290>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f853e17e320>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f853e17e3b0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f853e17e440>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f853e17e4d0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f853e17e560>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f853e17e5f0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f853e17e680>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f0d132e1400>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f853e699580>"
     },
     "verbose": 1,
     "policy_kwargs": {},

ppo-LunarLander-v2/system_info.txt

@@ -1,4 +1,4 @@
-- OS: Linux-6.17.13-200.fc42.x86_64-x86_64-with-glibc2.41 # 1 SMP PREEMPT_DYNAMIC Thu Dec 18 22:18:24 UTC 2025
+- OS: Linux-6.18.9-100.fc42.x86_64-x86_64-with-glibc2.41 # 1 SMP PREEMPT_DYNAMIC Fri Feb  6 18:42:22 UTC 2026
 - Python: 3.10.19
 - Stable-Baselines3: 2.0.0a5
 - PyTorch: 2.9.1+cu128
@@ -6,3 +6,4 @@
 - Numpy: 1.26.4
 - Cloudpickle: 3.1.2
 - Gymnasium: 0.28.1
+- OpenAI Gym: 0.22.0

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -178.6800656509379, "std_reward": 88.28303361708683, "n_evaluation_episodes": 10, "eval_datetime": "2026-02-16T23:07:16.504645"}
+{"mean_reward": 237.30941700000002, "std_reward": 19.256092091694153, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-16T23:17:52.000522"}