Upload PPO LunarLander-v2 trained agent

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 +16,22 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -141.75 +/- 89.18
+      value: 249.44 +/- 18.57
       name: mean_reward
       verified: false
 ---
 
-  # PPO Agent Playing LunarLander-v2
+# **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).
 
-  This is a trained model of a PPO agent playing LunarLander-v2.
-    
-  # Hyperparameters
-  ```python
-  {'exp_name': 'ppo'
-'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': 50000
-'learning_rate': 0.00025
-'num_envs': 4
-'num_steps': 128
-'anneal_lr': True
-'gae': True
-'gamma': 0.99
-'gae_lambda': 0.95
-'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': 'PhoenixA/ppo-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
-  ```
-  
+## 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 0x7b2cbdc62f20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b2cbdc62fc0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b2cbdc63060>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b2cbdc63100>", "_build": "<function ActorCriticPolicy._build at 0x7b2cbdc631a0>", "forward": "<function ActorCriticPolicy.forward at 0x7b2cbdc63240>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b2cbdc632e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b2cbdc63380>", "_predict": "<function ActorCriticPolicy._predict at 0x7b2cbdc63420>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b2cbdc634c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b2cbdc63560>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b2cbdc63600>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b2cbdd6c1c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000.0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1768312035814896080, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_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": 248, "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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "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-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct  2 10:42:05 UTC 2025", "Python": "3.12.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.9.0+cu126", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.2", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
+{"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 0x79cc9e2ce660>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79cc9e2ce700>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79cc9e2ce7a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79cc9e2ce840>", "_build": "<function ActorCriticPolicy._build at 0x79cc9e2ce8e0>", "forward": "<function ActorCriticPolicy.forward at 0x79cc9e2ce980>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x79cc9e2cea20>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79cc9e2ceac0>", "_predict": "<function ActorCriticPolicy._predict at 0x79cc9e2ceb60>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79cc9e2cec00>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79cc9e2ceca0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x79cc9e2ced40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x79cc9e3fee40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1775678289730050264, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdgIAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAAIAAAAAAABzU9+94VqNuNIW6DYCBJYyQC70OwwYC7YAAIA/AAAAAFppvr2PziC6K+bFtjmjfLK1p0c7DbroNQAAAAAAAIA/MyQivnwi8D4Sgpo94VlFvoUGRjyOrIc9AAAAAAAAAAAAQHO9rgfZukaWKDwrM/87pk6Gu3tD5DwAAIA/AACAP5rzo7xKuqo/HvQ6vlqrwr4FSPG7CDtTvAAAAAAAAAAAGgjDvUMcLbx6JJw8NXWSPPqmjz3eqnG9AACAPwAAAADaGQS+EKU/PzfdIL5S256+IkvtvWtczLwAAAAAAAAAAM3cJrs5dXU/QqJTPX7Q1b728bQ9KXQpvQAAAAAAAAAAmgjOvXs+j7pMJLY2Bou0Mf2UmroQkNe1AACAPwAAgD+aomQ9ksidP2aJvz6qdwO/rrczvUgA2jwAAAAAAAAAAABFtT24EBo/5QCJvuxJfr6Ekc+83IIsvQAAAAAAAAAABkdCvliJpz+amdC+UXf2vuJdOr4DuU85AAAAAAAAAABmkmO8j+42ujiW17iPXr2zZrUKumic/zcAAIA/AACAP/NdiL1I45S6rg8ztOCxm64AeSq6CPSYMwAAgD8AAIA/jcFrvrSS9bzw7G276SMFur/pVz5VfZs6AACAPwAAgD9a1pW9fCGJP8AvYL4RBKq+vb0fvfJ6Ub0AAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLEEsIhpSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_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": 248, "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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "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-6.6.113+-x86_64-with-glibc2.35 # 1 SMP Mon Feb  2 12:27:57 UTC 2026", "Python": "3.12.13", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.10.0+cu128", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.2", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b62a507a349d7714ffef375bfefc7b628cc709cf685c424bb0ed1c8f09ab354
-size 149177
+oid sha256:40e506914877127d233a5c44d2b28923b023e68aea37323a603c48eff1c5c2d7
+size 149172

ppo-LunarLander-v2/data

@@ -4,34 +4,34 @@
         ":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 0x7b2cbdc62f20>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b2cbdc62fc0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b2cbdc63060>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b2cbdc63100>",
-        "_build": "<function ActorCriticPolicy._build at 0x7b2cbdc631a0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7b2cbdc63240>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b2cbdc632e0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b2cbdc63380>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7b2cbdc63420>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b2cbdc634c0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b2cbdc63560>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b2cbdc63600>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x79cc9e2ce660>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79cc9e2ce700>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79cc9e2ce7a0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79cc9e2ce840>",
+        "_build": "<function ActorCriticPolicy._build at 0x79cc9e2ce8e0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x79cc9e2ce980>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x79cc9e2cea20>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79cc9e2ceac0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x79cc9e2ceb60>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79cc9e2cec00>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79cc9e2ceca0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x79cc9e2ced40>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7b2cbdd6c1c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x79cc9e3fee40>"
     },
     "verbose": 1,
     "policy_kwargs": {},
     "num_timesteps": 1015808,
-    "_total_timesteps": 1000000.0,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1768312035814896080,
+    "start_time": 1775678289730050264,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -45,7 +45,7 @@
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7390f4ee728bb400fbaa815aa28807fa701f9f0445eb4870bfac91f98a3e53cc
+oid sha256:8fa316954da1c87a141d6d736d2963742213304ed5f920864c601f8cfa377c43
 size 88695

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3019174e2c074aa279b6fe5767724a27b12cc69d9556682f233520f760bb9da1
+oid sha256:a9677b9d8309c296a22d4531006658e36e688c821256ef8404175036ad80b10a
 size 44095

ppo-LunarLander-v2/system_info.txt

@@ -1,7 +1,7 @@
-- OS: Linux-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct  2 10:42:05 UTC 2025
-- Python: 3.12.12
+- OS: Linux-6.6.113+-x86_64-with-glibc2.35 # 1 SMP Mon Feb  2 12:27:57 UTC 2026
+- Python: 3.12.13
 - Stable-Baselines3: 2.0.0a5
-- PyTorch: 2.9.0+cu126
+- PyTorch: 2.10.0+cu128
 - GPU Enabled: True
 - Numpy: 2.0.2
 - Cloudpickle: 3.1.2

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af8dc86be69437423c9e5671f9a8a6f982baf33b204f900f06c028d0b354b7f4
-size 31968
+oid sha256:0f3d07f196962a6421f67179b97882a1c1bddd81e12435dbfe3515587e0839e9
+size 163797

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -141.75269780284535, "std_reward": 89.18104631728455, "n_evaluation_episodes": 10, "eval_datetime": "2026-04-08T18:45:40.602203"}
+{"mean_reward": 249.44340651014028, "std_reward": 18.566346209738164, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-08T20:20:08.743902"}