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:
@@ -17,14 +16,22 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -129.27 +/- 85.80
+      value: 233.65 +/- 30.08
       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.
+## Usage (with Stable-baselines3)
+TODO: Add your code
 
-  # Hyperparameters
-  
+
+```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 0x000001B1191C2CA0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001B1191C2D40>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001B1191C2DE0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001B1191C2E80>", "_build": "<function ActorCriticPolicy._build at 0x000001B1191C2F20>", "forward": "<function ActorCriticPolicy.forward at 0x000001B1191C2FC0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x000001B1191C3060>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001B1191C3100>", "_predict": "<function ActorCriticPolicy._predict at 0x000001B1191C31A0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001B1191C3240>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001B1191C32E0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001B1191C3380>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000001B117E59600>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 5000192, "_total_timesteps": 5000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1694224638586413100, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAKZBwj74EIs/SxOiPtoyAr/hQ8g+WKCvvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -3.8399999999993994e-05, "_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": 19532, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "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:": "gAWVlwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwiVAZcAiQFTAJROhZQpjAFflIWUjFZDOlxVc2Vyc1xiZG9ublxtaW5pY29uZGEzXGVudnNcRFJMXExpYlxzaXRlLXBhY2thZ2VzXHN0YWJsZV9iYXNlbGluZXMzXGNvbW1vblx1dGlscy5weZSMBGZ1bmOUjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlEuEQwj4gADYDxKICpRDAJSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UaAx1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGggfZR9lChoGGgNjAxfX3F1YWxuYW1lX1+UaA6MD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBmMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP8mZmZmZmZqFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Windows-10-10.0.19045-SP0 10.0.19045", "Python": "3.11.4", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "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 0x000002513D05B370>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000002513D05B400>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000002513D05B490>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000002513D05B520>", "_build": "<function ActorCriticPolicy._build at 0x000002513D05B5B0>", "forward": "<function ActorCriticPolicy.forward at 0x000002513D05B640>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x000002513D05B6D0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000002513D05B760>", "_predict": "<function ActorCriticPolicy._predict at 0x000002513D05B7F0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000002513D05B880>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000002513D05B910>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x000002513D05B9A0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000002513D064380>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1694622532116602600, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAABrkDb3hiAE/O4nvvK2nZL5gyoa88bMQvAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.00044800000000000395, "_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": 3908, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "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": "Windows-10-10.0.19045-SP0 10.0.19045", "Python": "3.10.12", "Stable-Baselines3": "2.1.0", "PyTorch": "2.0.1", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.26.2"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa0e1aba2d514c659d7534ac801b47a52f6b434cfc3900d87d97fd09d81484f4
-size 145866
+oid sha256:1f7a670f3e1b088a9b726215f7da0cf149eb8c151c1fae571b20c8a46767e561
+size 145961

ppo-LunarLander-v2/_stable_baselines3_version

@@ -1 +1 @@
-2.0.0a5
+2.1.0

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 0x000001B1191C2CA0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001B1191C2D40>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001B1191C2DE0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001B1191C2E80>",
-        "_build": "<function ActorCriticPolicy._build at 0x000001B1191C2F20>",
-        "forward": "<function ActorCriticPolicy.forward at 0x000001B1191C2FC0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x000001B1191C3060>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001B1191C3100>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x000001B1191C31A0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001B1191C3240>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001B1191C32E0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001B1191C3380>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x000002513D05B370>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000002513D05B400>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000002513D05B490>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000002513D05B520>",
+        "_build": "<function ActorCriticPolicy._build at 0x000002513D05B5B0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x000002513D05B640>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x000002513D05B6D0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000002513D05B760>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x000002513D05B7F0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000002513D05B880>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000002513D05B910>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x000002513D05B9A0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x000001B117E59600>"
+        "_abc_impl": "<_abc._abc_data object at 0x000002513D064380>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 5000192,
-    "_total_timesteps": 5000000,
+    "num_timesteps": 1000448,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1694224638586413100,
+    "start_time": 1694622532116602600,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAKZBwj74EIs/SxOiPtoyAr/hQ8g+WKCvvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAABrkDb3hiAE/O4nvvK2nZL5gyoa88bMQvAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -41,17 +41,17 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -3.8399999999993994e-05,
+    "_current_progress_remaining": -0.00044800000000000395,
     "_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'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 19532,
+    "_n_updates": 3908,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -87,13 +87,13 @@
     "n_epochs": 4,
     "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,
     "lr_schedule": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     }
 }

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02ef68daf69b5c17809e8984753d712b4567fa6de265062f30744bb49361c272
+oid sha256:c59e6fc81a51ed5ec1ae24554344bec9d5fe7469ccd3be61a15d02c52db00e28
 size 87929

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e262fb27d589775e2c9f59b5409c3a25fc9d7e2fed30b30e6514e5573a40a17d
+oid sha256:1097ab295762813d40183c63c4da027ae4f4ef124f4c4cb285f6eae7b1734d97
 size 43329

ppo-LunarLander-v2/system_info.txt

@@ -1,8 +1,9 @@
 - OS: Windows-10-10.0.19045-SP0 10.0.19045
-- Python: 3.11.4
-- Stable-Baselines3: 2.0.0a5
-- PyTorch: 2.0.1+cu118
+- Python: 3.10.12
+- Stable-Baselines3: 2.1.0
+- PyTorch: 2.0.1
 - GPU Enabled: True
 - Numpy: 1.25.2
 - Cloudpickle: 2.2.1
 - Gymnasium: 0.28.1
+- OpenAI Gym: 0.26.2

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -129.27312842510733, "std_reward": 85.80198625228086, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T11:20:48.435323"}
+{"mean_reward": 233.64714270000005, "std_reward": 30.082866172370103, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-13T13:14:32.050553"}