Tuned PPO agent trained on LunarLander-v2 (1 million timesteps)

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 271.50 +/- 29.53
+      value: 282.31 +/- 20.05
       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 0x7faee4121750>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7faee41217e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7faee4121870>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7faee4121900>", "_build": "<function ActorCriticPolicy._build at 0x7faee4121990>", "forward": "<function ActorCriticPolicy.forward at 0x7faee4121a20>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7faee4121ab0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7faee4121b40>", "_predict": "<function ActorCriticPolicy._predict at 0x7faee4121bd0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7faee4121c60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7faee4121cf0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7faee4121d80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7faee4126e40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1708511698400829286, "learning_rate": {":type:": "<class 'function'>", ":serialized:": "gAWVlwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAksTQwh8AIgAFABTAJSMQQogICAgICAgIFByb2dyZXNzIHdpbGwgZGVjcmVhc2UgZnJvbSAxIChiZWdpbm5pbmcpIHRvIDAuCiAgICAgICAglIWUKYwScHJvZ3Jlc3NfcmVtYWluaW5nlIWUjCEvdG1wL2lweWtlcm5lbF81Mjc5LzExNjIwMjc0NTIucHmUjARmdW5jlEsHQwIIBJSMDWluaXRpYWxfdmFsdWWUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UTowIX19uYW1lX1+UjAhfX21haW5fX5R1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlGgAjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoHX2UfZQoaBZoDowMX19xdWFsbmFtZV9flIwdbGluZWFyX3NjaGVkdWxlLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZQojBJwcm9ncmVzc19yZW1haW5pbmeUjAhidWlsdGluc5SMBWZsb2F0lJOUjAZyZXR1cm6UaCl1jA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5RoCYwLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP2iTdLxqfvqFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="}, "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, "n_steps": 1024, "gamma": 0.99, "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 0x7faee40c69e0>", "reset": "<function RolloutBuffer.reset at 0x7faee40c6a70>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7faee40c6b00>", "add": "<function RolloutBuffer.add at 0x7faee40c6b90>", "get": "<function RolloutBuffer.get at 0x7faee40c6c20>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7faee40c6cb0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7faee40c3580>"}, "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, "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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.5.0-18-generic-x86_64-with-glibc2.35 # 18~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Feb  7 11:40:03 UTC 2", "Python": "3.10.12", "Stable-Baselines3": "2.2.1", "PyTorch": "2.0.1+cu117", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1", "OpenAI Gym": "0.26.2"}}
+{"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 0x7f0e8b840af0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0e8b840b80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0e8b840c10>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0e8b840ca0>", "_build": "<function ActorCriticPolicy._build at 0x7f0e8b840d30>", "forward": "<function ActorCriticPolicy.forward at 0x7f0e8b840dc0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f0e8b840e50>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0e8b840ee0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f0e8b840f70>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0e8b841000>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0e8b841090>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0e8b841120>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f0e8b83d1c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1708511698400829286, "learning_rate": {":type:": "<class 'function'>", ":serialized:": "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"}, "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, "n_steps": 1024, "gamma": 0.99, "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 0x7f0e8bb63eb0>", "reset": "<function RolloutBuffer.reset at 0x7f0e8bb63f40>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7f0e8b97c040>", "add": "<function RolloutBuffer.add at 0x7f0e8b97c0d0>", "get": "<function RolloutBuffer.get at 0x7f0e8b97c160>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7f0e8b97c1f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f0e8bb6ba00>"}, "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, "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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.5.0-21-generic-x86_64-with-glibc2.35 # 21~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Fri Feb  9 13:32:52 UTC 2", "Python": "3.10.12", "Stable-Baselines3": "2.2.1", "PyTorch": "2.0.1+cu117", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1", "OpenAI Gym": "0.26.2"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7ac254788c51bafe34c0b11ffb360ef2e674aaba560eb719a62b7f70582c617
+oid sha256:77f4a3e7eb0602b3dff6983b132da8e176226c6b56d67695143d74bbcf0e973d
 size 149969

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 0x7faee4121750>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7faee41217e0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7faee4121870>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7faee4121900>",
-        "_build": "<function ActorCriticPolicy._build at 0x7faee4121990>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7faee4121a20>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7faee4121ab0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7faee4121b40>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7faee4121bd0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7faee4121c60>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7faee4121cf0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7faee4121d80>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f0e8b840af0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0e8b840b80>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0e8b840c10>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0e8b840ca0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f0e8b840d30>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f0e8b840dc0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f0e8b840e50>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0e8b840ee0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f0e8b840f70>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0e8b841000>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0e8b841090>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0e8b841120>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7faee4126e40>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f0e8b83d1c0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -67,14 +67,14 @@
         "__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 0x7faee40c69e0>",
-        "reset": "<function RolloutBuffer.reset at 0x7faee40c6a70>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7faee40c6b00>",
-        "add": "<function RolloutBuffer.add at 0x7faee40c6b90>",
-        "get": "<function RolloutBuffer.get at 0x7faee40c6c20>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x7faee40c6cb0>",
+        "__init__": "<function RolloutBuffer.__init__ at 0x7f0e8bb63eb0>",
+        "reset": "<function RolloutBuffer.reset at 0x7f0e8bb63f40>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7f0e8b97c040>",
+        "add": "<function RolloutBuffer.add at 0x7f0e8b97c0d0>",
+        "get": "<function RolloutBuffer.get at 0x7f0e8b97c160>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x7f0e8b97c1f0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7faee40c3580>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f0e8bb6ba00>"
     },
     "rollout_buffer_kwargs": {},
     "batch_size": 64,

ppo-LunarLander-v2/system_info.txt

@@ -1,4 +1,4 @@
-- OS: Linux-6.5.0-18-generic-x86_64-with-glibc2.35 # 18~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Feb  7 11:40:03 UTC 2
+- OS: Linux-6.5.0-21-generic-x86_64-with-glibc2.35 # 21~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Fri Feb  9 13:32:52 UTC 2
 - Python: 3.10.12
 - Stable-Baselines3: 2.2.1
 - PyTorch: 2.0.1+cu117

results.json

@@ -1 +1 @@
-{"mean_reward": 271.4968271, "std_reward": 29.534047054395643, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-21T08:20:07.344138"}
+{"mean_reward": 282.3083673, "std_reward": 20.045812325246818, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-26T13:40:40.058680"}