Committed the Lunar Lander v2 - unit 1

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -868.51 +/- 410.32
+      value: 289.41 +/- 19.65
       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 0x0000021F159BD9E0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x0000021F159BDA80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x0000021F159BDB20>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x0000021F159BDBC0>", "_build": "<function ActorCriticPolicy._build at 0x0000021F159BDC60>", "forward": "<function ActorCriticPolicy.forward at 0x0000021F159BDD00>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x0000021F159BDDA0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x0000021F159BDE40>", "_predict": "<function ActorCriticPolicy._predict at 0x0000021F159BDEE0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x0000021F159BDF80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x0000021F159BE020>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x0000021F159BE0C0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x0000021F159C4C00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2048, "_total_timesteps": 10, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1701207023492603800, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAADODqLpjh7g/ST85vbbT9z4jLp06VT/DOwAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -203.8, "_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": 10, "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": 1, "n_steps": 2048, "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 0x0000021F1594E520>", "reset": "<function RolloutBuffer.reset at 0x0000021F1594E5C0>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x0000021F1594E660>", "add": "<function RolloutBuffer.add at 0x0000021F1594E7A0>", "get": "<function RolloutBuffer.get at 0x0000021F1594E840>", "_get_samples": "<function RolloutBuffer._get_samples at 0x0000021F1594E8E0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x0000021F15949B00>"}, "rollout_buffer_kwargs": {}, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Windows-10-10.0.22621-SP0 10.0.22621", "Python": "3.11.0", "Stable-Baselines3": "2.2.1", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.26.2", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1"}}
+{"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 0x000002243212D9E0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000002243212DA80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000002243212DB20>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000002243212DBC0>", "_build": "<function ActorCriticPolicy._build at 0x000002243212DC60>", "forward": "<function ActorCriticPolicy.forward at 0x000002243212DD00>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x000002243212DDA0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000002243212DE40>", "_predict": "<function ActorCriticPolicy._predict at 0x000002243212DEE0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000002243212DF80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000002243212E020>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x000002243212E0C0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x00000224321310C0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 10027008, "_total_timesteps": 10000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1701207231832605500, "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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAABAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0027007999999999477, "_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": 3060, "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": 2048, "gamma": 0.995, "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 0x00000224320BE520>", "reset": "<function RolloutBuffer.reset at 0x00000224320BE5C0>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x00000224320BE660>", "add": "<function RolloutBuffer.add at 0x00000224320BE7A0>", "get": "<function RolloutBuffer.get at 0x00000224320BE840>", "_get_samples": "<function RolloutBuffer._get_samples at 0x00000224320BE8E0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x00000224320BA080>"}, "rollout_buffer_kwargs": {}, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Windows-10-10.0.22621-SP0 10.0.22621", "Python": "3.11.0", "Stable-Baselines3": "2.2.1", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.26.2", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55c2f963ef1a93f65246193caf8dd7098634f382010df92f447bb8c405e659aa
-size 144946
+oid sha256:585f950affab99833b849f570b45477185762224114cd44eed7831bd40de35e2
+size 148715

ppo-LunarLander-v2/data

@@ -4,54 +4,54 @@
         ":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 0x0000021F159BD9E0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x0000021F159BDA80>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x0000021F159BDB20>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x0000021F159BDBC0>",
-        "_build": "<function ActorCriticPolicy._build at 0x0000021F159BDC60>",
-        "forward": "<function ActorCriticPolicy.forward at 0x0000021F159BDD00>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x0000021F159BDDA0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x0000021F159BDE40>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x0000021F159BDEE0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x0000021F159BDF80>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x0000021F159BE020>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x0000021F159BE0C0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x000002243212D9E0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000002243212DA80>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000002243212DB20>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000002243212DBC0>",
+        "_build": "<function ActorCriticPolicy._build at 0x000002243212DC60>",
+        "forward": "<function ActorCriticPolicy.forward at 0x000002243212DD00>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x000002243212DDA0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000002243212DE40>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x000002243212DEE0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000002243212DF80>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000002243212E020>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x000002243212E0C0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x0000021F159C4C00>"
+        "_abc_impl": "<_abc._abc_data object at 0x00000224321310C0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 2048,
-    "_total_timesteps": 10,
+    "num_timesteps": 10027008,
+    "_total_timesteps": 10000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1701207023492603800,
+    "start_time": 1701207231832605500,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAADODqLpjh7g/ST85vbbT9z4jLp06VT/DOwAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAABAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
     },
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -203.8,
+    "_current_progress_remaining": -0.0027007999999999477,
     "_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": 10,
+    "_n_updates": 3060,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -76,9 +76,9 @@
         "dtype": "int64",
         "_np_random": null
     },
-    "n_envs": 1,
+    "n_envs": 16,
     "n_steps": 2048,
-    "gamma": 0.999,
+    "gamma": 0.995,
     "gae_lambda": 0.98,
     "ent_coef": 0.01,
     "vf_coef": 0.5,
@@ -89,14 +89,14 @@
         "__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 0x0000021F1594E520>",
-        "reset": "<function RolloutBuffer.reset at 0x0000021F1594E5C0>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x0000021F1594E660>",
-        "add": "<function RolloutBuffer.add at 0x0000021F1594E7A0>",
-        "get": "<function RolloutBuffer.get at 0x0000021F1594E840>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x0000021F1594E8E0>",
+        "__init__": "<function RolloutBuffer.__init__ at 0x00000224320BE520>",
+        "reset": "<function RolloutBuffer.reset at 0x00000224320BE5C0>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x00000224320BE660>",
+        "add": "<function RolloutBuffer.add at 0x00000224320BE7A0>",
+        "get": "<function RolloutBuffer.get at 0x00000224320BE840>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x00000224320BE8E0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x0000021F15949B00>"
+        "_abc_impl": "<_abc._abc_data object at 0x00000224320BA080>"
     },
     "rollout_buffer_kwargs": {},
     "batch_size": 64,

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2f87b50bb16bdafb0ce998c9a6ea1216e4986a70bd01cda01078cc5b4b44dfa
+oid sha256:58b3580d0c9ab64b942e11dc56c6d5c4fe7a24ef5d5c1e39d4447b32d429b503
 size 87929

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1447879c21c30e1eb126e78362e7ac4f8b2a21b358d2f427f0e182016c27698
+oid sha256:bddad8ef1b5dbaadd5a470fb2e7eb1d05b73e68d6d0699546b7df95e1ce0789d
 size 43329

results.json

@@ -1 +1 @@
-{"mean_reward": -868.5105301, "std_reward": 410.32274713550356, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-28T15:30:45.158104"}
+{"mean_reward": 289.4056432, "std_reward": 19.649004674547438, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-29T12:56:49.965962"}