Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 261.71 +/- 21.03
+      value: -5.46 +/- 107.66
       name: mean_reward
       verified: false
 ---

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 0x7a17677c1c60>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a17677c1cf0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a17677c1d80>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a17677c1e10>", "_build": "<function ActorCriticPolicy._build at 0x7a17677c1ea0>", "forward": "<function ActorCriticPolicy.forward at 0x7a17677c1f30>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a17677c1fc0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a17677c2050>", "_predict": "<function ActorCriticPolicy._predict at 0x7a17677c20e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a17677c2170>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a17677c2200>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a17677c2290>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7a17677bb480>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1713261332821697715, "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:": "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": 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": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]", "low_repr": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high_repr": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 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": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}", "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ", "__init__": "<function RolloutBuffer.__init__ at 0x7a176791c820>", "reset": "<function RolloutBuffer.reset at 0x7a176791c8b0>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7a176791c940>", "add": "<function RolloutBuffer.add at 0x7a176791c9d0>", "get": "<function RolloutBuffer.get at 0x7a176791ca60>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7a176791caf0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7a1767915c80>"}, "rollout_buffer_kwargs": {}, "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-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.3.0", "PyTorch": "2.2.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "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 0x7fb2368d53f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb2368d5480>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb2368d5510>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb2368d55a0>", "_build": "<function ActorCriticPolicy._build at 0x7fb2368d5630>", "forward": "<function ActorCriticPolicy.forward at 0x7fb2368d56c0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fb2368d5750>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb2368d57e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fb2368d5870>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb2368d5900>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb2368d5990>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb2368d5a20>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fb2370cbb40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1713472750456789429, "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:": "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": 3100, "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": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]", "low_repr": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high_repr": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 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": 16, "n_steps": 1024, "gamma": 0.95, "gae_lambda": 0.54, "ent_coef": 0.03, "vf_coef": 0.5, "max_grad_norm": 0.5, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}", "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ", "__init__": "<function RolloutBuffer.__init__ at 0x7fb236b03f40>", "reset": "<function RolloutBuffer.reset at 0x7fb236b24040>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7fb236b240d0>", "add": "<function RolloutBuffer.add at 0x7fb236b24160>", "get": "<function RolloutBuffer.get at 0x7fb236b241f0>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7fb236b24280>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fb236b202c0>"}, "rollout_buffer_kwargs": {}, "batch_size": 64, "n_epochs": 5, "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-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.3.0", "PyTorch": "2.2.1+cu121", "GPU Enabled": "False", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79b7a515460f8fe1ed94c2577d0b9e70b549410873f02a51775ad3cb4140f6a6
-size 150287
+oid sha256:f651f50053fcf46bd58e1b41da2371e4e1a880d4d2cd5e729c1582a961ae5fa3
+size 149788

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 0x7a17677c1c60>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a17677c1cf0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a17677c1d80>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a17677c1e10>",
-        "_build": "<function ActorCriticPolicy._build at 0x7a17677c1ea0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7a17677c1f30>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a17677c1fc0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a17677c2050>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7a17677c20e0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a17677c2170>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a17677c2200>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a17677c2290>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fb2368d53f0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb2368d5480>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb2368d5510>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb2368d55a0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fb2368d5630>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fb2368d56c0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fb2368d5750>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb2368d57e0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fb2368d5870>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb2368d5900>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb2368d5990>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb2368d5a20>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7a17677bb480>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fb2370cbb40>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -26,12 +26,12 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1713261332821697715,
+    "start_time": 1713472750456789429,
     "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'>",
@@ -45,13 +45,13 @@
     "_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": 248,
+    "_n_updates": 3100,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -78,9 +78,9 @@
     },
     "n_envs": 16,
     "n_steps": 1024,
-    "gamma": 0.999,
-    "gae_lambda": 0.98,
-    "ent_coef": 0.01,
+    "gamma": 0.95,
+    "gae_lambda": 0.54,
+    "ent_coef": 0.03,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
     "rollout_buffer_class": {
@@ -89,18 +89,18 @@
         "__module__": "stable_baselines3.common.buffers",
         "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}",
         "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ",
-        "__init__": "<function RolloutBuffer.__init__ at 0x7a176791c820>",
-        "reset": "<function RolloutBuffer.reset at 0x7a176791c8b0>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7a176791c940>",
-        "add": "<function RolloutBuffer.add at 0x7a176791c9d0>",
-        "get": "<function RolloutBuffer.get at 0x7a176791ca60>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x7a176791caf0>",
+        "__init__": "<function RolloutBuffer.__init__ at 0x7fb236b03f40>",
+        "reset": "<function RolloutBuffer.reset at 0x7fb236b24040>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7fb236b240d0>",
+        "add": "<function RolloutBuffer.add at 0x7fb236b24160>",
+        "get": "<function RolloutBuffer.get at 0x7fb236b241f0>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x7fb236b24280>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7a1767915c80>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fb236b202c0>"
     },
     "rollout_buffer_kwargs": {},
     "batch_size": 64,
-    "n_epochs": 4,
+    "n_epochs": 5,
     "clip_range": {
         ":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 sha256:8189c6fdfcca075186fd905188350dc536af7421ac6df63a81161241ce0a9303
-size 88362
+oid sha256:90728adcfb7a1191d1ebec94ee36e3ae7e01f7831d91f221bc86f18032c459ff
+size 87978

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ad4150b56feb3ff821511432d70c39954c566aacb6e5b05c78e675d61ab3d0e
-size 43762
+oid sha256:fd1359598d363c10d1dc11a6a606f32eda1632d7dea87f3bad75fcc57545d0b2
+size 43634

ppo-LunarLander-v2/system_info.txt

@@ -2,7 +2,7 @@
 - Python: 3.10.12
 - Stable-Baselines3: 2.3.0
 - PyTorch: 2.2.1+cu121
-- GPU Enabled: True
+- GPU Enabled: False
 - Numpy: 1.25.2
 - Cloudpickle: 2.2.1
 - Gymnasium: 0.29.1

results.json

@@ -1 +1 @@
-{"mean_reward": 261.7099007965088, "std_reward": 21.0334037954068, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-16T10:26:29.238227"}
+{"mean_reward": -5.462944042716231, "std_reward": 107.65807334999677, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-18T21:29:50.670014"}