Upload folder using huggingface_hub

.gitattributes

@@ -25,6 +25,7 @@
 *.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text

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: -136.79 +/- 101.06
+      value: 293.53 +/- 8.50
       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
-  {'repo_id': 'ThePianist/ppo-LunarLander-v2'
-'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
-'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 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 0x7fc114ad25e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc114ad2670>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc114ad2700>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc114ad2790>", "_build": "<function ActorCriticPolicy._build at 0x7fc114ad2820>", "forward": "<function ActorCriticPolicy.forward at 0x7fc114ad28b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc114ad2940>", "_predict": "<function ActorCriticPolicy._predict at 0x7fc114ad29d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc114ad2a60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc114ad2af0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc114ad2b80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fc114ac8e40>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670539813869382065, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_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, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVTxAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIA7aDEXtuckCUhpRSlIwBbJRNMgGMAXSUR0Cet7mHP/rCdX2UKGgGaAloD0MIO8JpwUs8c0CUhpRSlGgVTVkBaBZHQJ65IACGN711fZQoaAZoCWgPQwgnamluBfRxQJSGlFKUaBVNTwFoFkdAnrsMO9WZJHV9lChoBmgJaA9DCMb3xaUqxXFAlIaUUpRoFU0FAWgWR0CevEvEjxCqdX2UKGgGaAloD0MIiSR6GQW1cUCUhpRSlGgVTQgBaBZHQJ69Mw35vcd1fZQoaAZoCWgPQwi+MQQAx9IzwJSGlFKUaBVLqmgWR0CevV4j8k2QdX2UKGgGaAloD0MIuAGfH0aXcECUhpRSlGgVS/loFkdAnr7AdOqNqHV9lChoBmgJaA9DCMFxGTe16nFAlIaUUpRoFU0nAWgWR0CevtYAKfFrdX2UKGgGaAloD0MIL2zNVt7bcUCUhpRSlGgVTYsBaBZHQJ6+7UDuBtl1fZQoaAZoCWgPQwhEUaBP5OVbQJSGlFKUaBVN6ANoFkdAnr8XRb8m8nV9lChoBmgJaA9DCIxIFFoWrXFAlIaUUpRoFU0XAWgWR0Cev5sA/9pAdX2UKGgGaAloD0MINEdWflnacECUhpRSlGgVS/ZoFkdAnsAFymygPHV9lChoBmgJaA9DCBztuOH3vm9AlIaUUpRoFU0OAWgWR0CewNarmyPddX2UKGgGaAloD0MIvXK9baY8cUCUhpRSlGgVS95oFkdAnsE0YCQtBnV9lChoBmgJaA9DCLhWe9iLwnBAlIaUUpRoFU0uAWgWR0Cewk+UyHmBdX2UKGgGaAloD0MIpG5nXzlycECUhpRSlGgVTQIBaBZHQJ7EN7BwdbR1fZQoaAZoCWgPQwhcGyrGubJxQJSGlFKUaBVL42gWR0CexEoW56MSdX2UKGgGaAloD0MIUYTU7WzobkCUhpRSlGgVS/RoFkdAnsW2lyimEXV9lChoBmgJaA9DCPhVuVB5CHFAlIaUUpRoFUvXaBZHQJ7GMSHuZ1F1fZQoaAZoCWgPQwg6QZscfjlwQJSGlFKUaBVL/2gWR0CexkKekHlfdX2UKGgGaAloD0MIi6n0E87db0CUhpRSlGgVS99oFkdAnsZnBP9DQnV9lChoBmgJaA9DCHf0v1yLQ3JAlIaUUpRoFU0JAWgWR0Cex9TkQwsYdX2UKGgGaAloD0MI121Q+20ocUCUhpRSlGgVTQgBaBZHQJ7IFB+nZTR1fZQoaAZoCWgPQwitUQ/RaCpyQJSGlFKUaBVL7WgWR0CeyQNcnmaIdX2UKGgGaAloD0MIbRtGQfC+ckCUhpRSlGgVTRsBaBZHQJ7JRSJj2Bd1fZQoaAZoCWgPQwggJXZt7+NvQJSGlFKUaBVNFwFoFkdAnsmUPtlZo3V9lChoBmgJaA9DCLfRAN6CfXBAlIaUUpRoFU0AAWgWR0Cey0BpYcNpdX2UKGgGaAloD0MIGZKTiZsacECUhpRSlGgVS+ZoFkdAnsxhDkU9IXV9lChoBmgJaA9DCEImGTlLAHJAlIaUUpRoFU1QAWgWR0CezMcsUZeidX2UKGgGaAloD0MI1xLyQc/KQ0CUhpRSlGgVS9doFkdAns06gM+eOHV9lChoBmgJaA9DCNmTwOacWHJAlIaUUpRoFU0AAWgWR0CezTrUb1h9dX2UKGgGaAloD0MI+pl63WJJcUCUhpRSlGgVS/BoFkdAns5/0NBnjHV9lChoBmgJaA9DCPFL/bwpiGxAlIaUUpRoFUvzaBZHQJ7O1tVJcxF1fZQoaAZoCWgPQwhD4bN1MC9zQJSGlFKUaBVNAwFoFkdAns88eCCjDnV9lChoBmgJaA9DCPyKNVykeXBAlIaUUpRoFUvtaBZHQJ7P+1rqMWJ1fZQoaAZoCWgPQwhvu9Bcp8BwQJSGlFKUaBVNAQFoFkdAntDc8kleGHV9lChoBmgJaA9DCCdok8OndHJAlIaUUpRoFUvmaBZHQJ7RFAv+OwR1fZQoaAZoCWgPQwi4Wicux6RtQJSGlFKUaBVNHQFoFkdAntLe7tiQT3V9lChoBmgJaA9DCH+mXrfIuXBAlIaUUpRoFU0XAWgWR0Ce00DZ13dLdX2UKGgGaAloD0MIBjBl4IA6cUCUhpRSlGgVS9VoFkdAntTT50r9VHV9lChoBmgJaA9DCKz9ne0RnnBAlIaUUpRoFUvzaBZHQJ7VFqVQhwF1fZQoaAZoCWgPQwj8q8d9qylwQJSGlFKUaBVL62gWR0Ce1bNPP9k0dX2UKGgGaAloD0MI8z0jERqeWUCUhpRSlGgVTegDaBZHQJ7WCflIVdp1fZQoaAZoCWgPQwhSmPc4Uz9gQJSGlFKUaBVN6ANoFkdAntYWyxA0K3V9lChoBmgJaA9DCKG5TiMtlWJAlIaUUpRoFU3oA2gWR0Ce1lnqFAVxdX2UKGgGaAloD0MIhnMNMzSXcUCUhpRSlGgVTRkBaBZHQJ7W1bHIZIh1fZQoaAZoCWgPQwg1t0JYjbZxQJSGlFKUaBVL+2gWR0Ce12QgLZzxdX2UKGgGaAloD0MI4KEo0CfNcUCUhpRSlGgVS/VoFkdAntd3J1aGH3V9lChoBmgJaA9DCAaDa+5oq3FAlIaUUpRoFUvxaBZHQJ7Xp7v5P/J1fZQoaAZoCWgPQwg6PlqcMRZwQJSGlFKUaBVL9mgWR0Ce2F3nIQvpdX2UKGgGaAloD0MIuXL2zqiscUCUhpRSlGgVS+5oFkdAntjkqtozvnV9lChoBmgJaA9DCHLChNGsXXFAlIaUUpRoFUv3aBZHQJ7ZT7TDwYt1fZQoaAZoCWgPQwifHXBdcedxQJSGlFKUaBVLu2gWR0Ce2mURFqi5dX2UKGgGaAloD0MIev1JfO7ycUCUhpRSlGgVTQQBaBZHQJ7bFwT/Q0J1fZQoaAZoCWgPQwjjVdY2haNxQJSGlFKUaBVL+WgWR0Ce3Kpi7TUidX2UKGgGaAloD0MI7uvAOaM4bECUhpRSlGgVTTUBaBZHQJ7dHueBg/l1fZQoaAZoCWgPQwiPq5Fd6dByQJSGlFKUaBVL72gWR0Ce3TB8x9G7dX2UKGgGaAloD0MIGysxz8ojbkCUhpRSlGgVTQgBaBZHQJ7dr3K0UoN1fZQoaAZoCWgPQwjvcDs0LAFvQJSGlFKUaBVL6WgWR0Ce3mTkQwsYdX2UKGgGaAloD0MIt9WsM752bkCUhpRSlGgVS+5oFkdAnt6jhtLteHV9lChoBmgJaA9DCNEi2/m+hXFAlIaUUpRoFU0mAWgWR0Ce3tmygPEsdX2UKGgGaAloD0MIWwndJTG1ckCUhpRSlGgVS+1oFkdAnt/Lrs0HhXV9lChoBmgJaA9DCLh3DfpSP3JAlIaUUpRoFU0IAWgWR0Ce38pIczZZdX2UKGgGaAloD0MI8gaY+Q4OTkCUhpRSlGgVS91oFkdAnt/g4bS7XnV9lChoBmgJaA9DCFOwxtm0mnBAlIaUUpRoFU1jAWgWR0Ce4RQT238XdX2UKGgGaAloD0MI8DUEx2XvcECUhpRSlGgVTQ0BaBZHQJ7hxFx4ptt1fZQoaAZoCWgPQwjKGvUQzeJwQJSGlFKUaBVL2GgWR0Ce4hE8aGYbdX2UKGgGaAloD0MIofKv5VXMckCUhpRSlGgVS/JoFkdAnuIuQ+2VmnV9lChoBmgJaA9DCJXwhF4/OHFAlIaUUpRoFU2RAWgWR0Ce4uNIK+i8dX2UKGgGaAloD0MIbqRskTQ1cECUhpRSlGgVS+xoFkdAnuRpDE3sHHV9lChoBmgJaA9DCFpmEYrtinJAlIaUUpRoFUvwaBZHQJ7lGCK77Kt1fZQoaAZoCWgPQwgt6SgH8/1wQJSGlFKUaBVL62gWR0Ce5iq0MPSVdX2UKGgGaAloD0MIRgckYd+xb0CUhpRSlGgVTQcBaBZHQJ7m41ZTyax1fZQoaAZoCWgPQwjbiZKQSFZvQJSGlFKUaBVL5mgWR0Ce5u3fAKv3dX2UKGgGaAloD0MISIjyBS3OSUCUhpRSlGgVS+RoFkdAnub3rIHTqnV9lChoBmgJaA9DCPuxSX7EqmtAlIaUUpRoFU0jAWgWR0Ce545kbxVidX2UKGgGaAloD0MIgJpattbDcECUhpRSlGgVTWABaBZHQJ7oLYkE9uB1fZQoaAZoCWgPQwiaIyu/TPNxQJSGlFKUaBVNEgFoFkdAnuhQ+UyHmHV9lChoBmgJaA9DCBIUP8Zcf3BAlIaUUpRoFUvqaBZHQJ7oZ1uBMBZ1fZQoaAZoCWgPQwjBAMKHUhVyQJSGlFKUaBVNgQFoFkdAnui4zvZyuXV9lChoBmgJaA9DCCL/zCD+W3FAlIaUUpRoFU0OAWgWR0Ce6mlHz6JqdX2UKGgGaAloD0MI4/24/TKvckCUhpRSlGgVS/ZoFkdAnuqBTGYKIHV9lChoBmgJaA9DCExPWOIBuXBAlIaUUpRoFU0tAWgWR0Ce6zxcVxjsdX2UKGgGaAloD0MI4zYawFu+Y0CUhpRSlGgVTegDaBZHQJ7rWNlyzX11fZQoaAZoCWgPQwjzWZ4Ht0lwQJSGlFKUaBVNAAFoFkdAnuw0bgjyF3V9lChoBmgJaA9DCEuRfCWQ+G5AlIaUUpRoFUv6aBZHQJ7slddE9dN1fZQoaAZoCWgPQwjhfyvZsRtuQJSGlFKUaBVL62gWR0Ce7QsLv1DjdX2UKGgGaAloD0MIZRwj2aNSbUCUhpRSlGgVS+5oFkdAnu24mXw9aHV9lChoBmgJaA9DCGthFto5kXFAlIaUUpRoFUvlaBZHQJ7uixiXpnp1fZQoaAZoCWgPQwiOsRNegrFuQJSGlFKUaBVL4GgWR0Ce7om9QGfPdX2UKGgGaAloD0MIgQabOs9ocUCUhpRSlGgVTSoBaBZHQJ7va2y9mHx1fZQoaAZoCWgPQwjGUbmJWvhwQJSGlFKUaBVN3QFoFkdAnu/mFzuF6HV9lChoBmgJaA9DCC/3yVGAqm9AlIaUUpRoFU0CAWgWR0Ce8Ab9ZRsNdX2UKGgGaAloD0MIuRgD67h5cUCUhpRSlGgVTUQBaBZHQJ7wvlijL0V1fZQoaAZoCWgPQwgYtJCA0bFIQJSGlFKUaBVLy2gWR0Ce8ODLbHp9dX2UKGgGaAloD0MIs9KkFDSIckCUhpRSlGgVS/toFkdAnvGIDcM3InV9lChoBmgJaA9DCPhT46Wb/D9AlIaUUpRoFUvMaBZHQJ7ySSntOVR1fZQoaAZoCWgPQwhrf2d79HdxQJSGlFKUaBVNKgFoFkdAnvLGHtWuHXV9lChoBmgJaA9DCNC3BUu1InBAlIaUUpRoFU0OAWgWR0Ce8twRoRI0dX2UKGgGaAloD0MIyjUFMruFbkCUhpRSlGgVS/NoFkdAnvPXDWK/EnVlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 310, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
+{"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 0x70ef761f7010>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x70ef761f70a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x70ef761f7130>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x70ef761f71c0>", "_build": "<function ActorCriticPolicy._build at 0x70ef761f7250>", "forward": "<function ActorCriticPolicy.forward at 0x70ef761f72e0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x70ef761f7370>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x70ef761f7400>", "_predict": "<function ActorCriticPolicy._predict at 0x70ef761f7490>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x70ef761f7520>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x70ef761f75b0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x70ef761f7640>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x70ef761ee800>"}, "verbose": 2, "policy_kwargs": {}, "num_timesteps": 2097152, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1728119189398796481, "learning_rate": 0.0001, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.04857599999999995, "_stats_window_size": 1, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpSwGGlFKULg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpSwGGlFKULg=="}, "_n_updates": 80, "n_steps": 4096, "gamma": 0.997, "gae_lambda": 0.95, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 512, "n_epochs": 5, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWV7QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMXS9ob21lL3Nvbm5uL21pbmljb25kYTMvZW52cy9STC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4RDAgQBlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMXS9ob21lL3Nvbm5uL21pbmljb25kYTMvZW52cy9STC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "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": "Generator(PCG64)"}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "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", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 32, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.8.0-45-generic-x86_64-with-glibc2.39 # 45-Ubuntu SMP PREEMPT_DYNAMIC Fri Aug 30 12:02:04 UTC 2024", "Python": "3.10.0", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.4.1+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34692e031e8e14538023e665f79ffc3aa1b98d8b297399d085a2cb4b401117b5
-size 147153
+oid sha256:d4911936d79d2f0f1ef0a0d4d76731b9f962674f1f7cafe0ae860a6fbee27466
+size 145472

ppo-LunarLander-v2/_stable_baselines3_version

@@ -1 +1 @@
-1.6.2
+2.0.0a5

ppo-LunarLander-v2/data

@@ -3,92 +3,97 @@
         ":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 0x7fc114ad25e0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc114ad2670>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc114ad2700>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc114ad2790>",
-        "_build": "<function ActorCriticPolicy._build at 0x7fc114ad2820>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7fc114ad28b0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc114ad2940>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7fc114ad29d0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc114ad2a60>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc114ad2af0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc114ad2b80>",
+        "__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 0x70ef761f7010>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x70ef761f70a0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x70ef761f7130>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x70ef761f71c0>",
+        "_build": "<function ActorCriticPolicy._build at 0x70ef761f7250>",
+        "forward": "<function ActorCriticPolicy.forward at 0x70ef761f72e0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x70ef761f7370>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x70ef761f7400>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x70ef761f7490>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x70ef761f7520>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x70ef761f75b0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x70ef761f7640>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7fc114ac8e40>"
+        "_abc_impl": "<_abc._abc_data object at 0x70ef761ee800>"
     },
-    "verbose": 1,
+    "verbose": 2,
     "policy_kwargs": {},
-    "observation_space": {
-        ":type:": "<class 'gym.spaces.box.Box'>",
-        ":serialized:": "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",
-        "dtype": "float32",
-        "_shape": [
-            8
-        ],
-        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
-        "high": "[inf inf inf inf inf inf inf inf]",
-        "bounded_below": "[False False False False False False False False]",
-        "bounded_above": "[False False False False False False False False]",
-        "_np_random": null
-    },
-    "action_space": {
-        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
-        "n": 4,
-        "_shape": [],
-        "dtype": "int64",
-        "_np_random": null
-    },
-    "n_envs": 16,
-    "num_timesteps": 1015808,
-    "_total_timesteps": 1000000,
+    "num_timesteps": 2097152,
+    "_total_timesteps": 2000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1670539813869382065,
-    "learning_rate": 0.0003,
+    "start_time": 1728119189398796481,
+    "learning_rate": 0.0001,
     "tensorboard_log": null,
-    "lr_schedule": {
-        ":type:": "<class 'function'>",
-        ":serialized:": "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"
-    },
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAKAvmr68FL8+rIe6PTlAqb5VEOe9igylPQAAAAAAAAAA8yYdvp0FRT+LM9u8vSXRvlHeyL1Cdgk+AAAAAAAAAAD6UEu+TLQRPnspmj2990a+u7nGu2bPlLwAAAAAAAAAAA1Fez5LaG8/7VfePuITAL9UuZM+8gzrPQAAAAAAAAAA85zwPfjt6j4SkfO9lNjovtfuRDzqHfO9AAAAAAAAAADg4Bq+vSMxPGZqgD1ptgq8ajDDvWRUBD0AAIA/AACAPwY0S76EXZk+2BeNPcLLLL7T5lC9w5JgPQAAAAAAAAAAGu9OPfbMNrre0ogz4PIULCsr17qC+MuzAACAPwAAgD/Na5g9veo2PCOAUr50nxS+v/S1vUMl+DsAAAAAAAAAAEBUUD5aYIg/DjLGPipD977vdIA+4qIEvQAAAAAAAAAA2if/vXGiIrsEDiA8nmteOsL9+Ts4diC7AACAPwAAgD8mUke+XINhvLDQZDq+/pg4dtzCPU6tVbkAAIA/AACAP5M1G76NWZ8+7kEuPrJWQr7Efz67eawwPQAAAAAAAAAABu+FPmeBJz7SbGa+Wl0hvoCJ6jz004a9AAAAAAAAAADNjLM7jBWxP26/MD7zt92+htaHup1UDz0AAAAAAAAAAPo+HD6uvcw9AfgkvqBFRb77PHG9htEXPAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="
     },
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.015808000000000044,
+    "_current_progress_remaining": -0.04857599999999995,
+    "_stats_window_size": 1,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpSwGGlFKULg=="
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpSwGGlFKULg=="
     },
-    "_n_updates": 310,
-    "n_steps": 2048,
-    "gamma": 0.99,
+    "_n_updates": 80,
+    "n_steps": 4096,
+    "gamma": 0.997,
     "gae_lambda": 0.95,
-    "ent_coef": 0.0,
+    "ent_coef": 0.01,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
-    "batch_size": 64,
-    "n_epochs": 10,
+    "batch_size": 512,
+    "n_epochs": 5,
     "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,
+    "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": "Generator(PCG64)"
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "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",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 32,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
 }

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19685fe8351b311b82a4117c8e22aa4b97eacc37dbdfd2037c7c550a7bc792af
-size 87929
+oid sha256:5ac1525cc48e7b2660e9314059d944e6429a9bf0cbdd7eb12c5fcbf8ae3da1fe
+size 88490

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a74cf9d35c3aa6dcdf30ea598249856ed59b985513f343c60ba8ff48c7974f8e
-size 43201
+oid sha256:8a29e8f0e189d3990a63d8369c0c145b45c6c476ec7d76d90e5958b18f6442ff
+size 43762

ppo-LunarLander-v2/pytorch_variables.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
-size 431
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

ppo-LunarLander-v2/system_info.txt

@@ -1,7 +1,8 @@
-OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
-Python: 3.8.16
-Stable-Baselines3: 1.6.2
-PyTorch: 1.13.0+cu116
-GPU Enabled: True
-Numpy: 1.21.6
-Gym: 0.21.0
+- OS: Linux-6.8.0-45-generic-x86_64-with-glibc2.39 # 45-Ubuntu SMP PREEMPT_DYNAMIC Fri Aug 30 12:02:04 UTC 2024
+- Python: 3.10.0
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.4.1+cu121
+- GPU Enabled: True
+- Numpy: 1.26.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d27114220783a63fb6c1faa82bae9de24d16239d0d7ffbf2d2d9451ffe1c434b
-size 30494
+oid sha256:cf5191159e72faa2c07ee9d055493726fa1268aafe9e3da3207d617a25f2e245
+size 156095

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -136.78785401195907, "std_reward": 101.06116285117363, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-23T05:56:36.570849"}
+{"mean_reward": 293.53462356481003, "std_reward": 8.498841384843148, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-05T17:08:59.746726"}