Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 266.34 +/- 12.95
+      value: 261.34 +/- 17.27
       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 0x7b8ebf9553a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b8ebf955440>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b8ebf9554e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b8ebf955580>", "_build": "<function ActorCriticPolicy._build at 0x7b8ebf955620>", "forward": "<function ActorCriticPolicy.forward at 0x7b8ebf9556c0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b8ebf955760>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b8ebf955800>", "_predict": "<function ActorCriticPolicy._predict at 0x7b8ebf9558a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b8ebf955940>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b8ebf9559e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b8ebf955a80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b8ebf947ac0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1722452713571050598, "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:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "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 0x7b8ec31ea2a0>", "reset": "<function RolloutBuffer.reset at 0x7b8ec31ea340>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7b8ec31ea3e0>", "add": "<function RolloutBuffer.add at 0x7b8ec31ea520>", "get": "<function RolloutBuffer.get at 0x7b8ec31ea5c0>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7b8ec31ea660>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b8ec31dee40>"}, "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-6.8.0-39-generic-x86_64-with-glibc2.39 # 39-Ubuntu SMP PREEMPT_DYNAMIC Fri Jul  5 21:49:14 UTC 2024", "Python": "3.12.4", "Stable-Baselines3": "2.3.2", "PyTorch": "2.4.0+cu121", "GPU Enabled": "True", "Numpy": "2.0.1", "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 0x7ddf63c17ec0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ddf63c17f60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ddf63c20040>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ddf63c200e0>", "_build": "<function ActorCriticPolicy._build at 0x7ddf63c20180>", "forward": "<function ActorCriticPolicy.forward at 0x7ddf63c20220>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ddf63c202c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ddf63c20360>", "_predict": "<function ActorCriticPolicy._predict at 0x7ddf63c20400>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ddf63c204a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ddf63c20540>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ddf63c205e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ddf63c18880>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1722452713571050598, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_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:": "gAWV/gAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoC4wCaTiUiYiHlFKUKEsDaA9OTk5K/////0r/////SwB0lGKMCl9ucF9yYW5kb22UTnViLg==", "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 0x7ddf63dbcea0>", "reset": "<function RolloutBuffer.reset at 0x7ddf63dbcf40>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7ddf63dbcfe0>", "add": "<function RolloutBuffer.add at 0x7ddf63dbd120>", "get": "<function RolloutBuffer.get at 0x7ddf63dbd1c0>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7ddf63dbd260>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ddf63d9fdc0>"}, "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-6.8.0-39-generic-x86_64-with-glibc2.39 # 39-Ubuntu SMP PREEMPT_DYNAMIC Fri Jul  5 21:49:14 UTC 2024", "Python": "3.12.4", "Stable-Baselines3": "2.3.2", "PyTorch": "2.4.0+cu121", "GPU Enabled": "True", "Numpy": "2.0.1", "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 sha256:79173f31bfcdba3359b6e41ea1b16f4bbcd7b35b0e8ad45c582f333ace5f71f4
-size 151053
+oid sha256:cfcd92929760f922a2b09281ee8e3d0bf7580f8c2714883f46ecdd8cd95cedb0
+size 150946

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 0x7b8ebf9553a0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b8ebf955440>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b8ebf9554e0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b8ebf955580>",
-        "_build": "<function ActorCriticPolicy._build at 0x7b8ebf955620>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7b8ebf9556c0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b8ebf955760>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b8ebf955800>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7b8ebf9558a0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b8ebf955940>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b8ebf9559e0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b8ebf955a80>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7ddf63c17ec0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ddf63c17f60>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ddf63c20040>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ddf63c200e0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7ddf63c20180>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7ddf63c20220>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ddf63c202c0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ddf63c20360>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7ddf63c20400>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ddf63c204a0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ddf63c20540>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ddf63c205e0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7b8ebf947ac0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7ddf63c18880>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -29,10 +29,7 @@
     "start_time": 1722452713571050598,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
-    "_last_obs": {
-        ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
-    },
+    "_last_obs": null,
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
         ":serialized:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="
@@ -69,7 +66,7 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu",
+        ":serialized:": "gAWV/gAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoC4wCaTiUiYiHlFKUKEsDaA9OTk5K/////0r/////SwB0lGKMCl9ucF9yYW5kb22UTnViLg==",
         "n": "4",
         "start": "0",
         "_shape": [],
@@ -89,21 +86,21 @@
         "__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 0x7b8ec31ea2a0>",
-        "reset": "<function RolloutBuffer.reset at 0x7b8ec31ea340>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7b8ec31ea3e0>",
-        "add": "<function RolloutBuffer.add at 0x7b8ec31ea520>",
-        "get": "<function RolloutBuffer.get at 0x7b8ec31ea5c0>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x7b8ec31ea660>",
+        "__init__": "<function RolloutBuffer.__init__ at 0x7ddf63dbcea0>",
+        "reset": "<function RolloutBuffer.reset at 0x7ddf63dbcf40>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7ddf63dbcfe0>",
+        "add": "<function RolloutBuffer.add at 0x7ddf63dbd120>",
+        "get": "<function RolloutBuffer.get at 0x7ddf63dbd1c0>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x7ddf63dbd260>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7b8ec31dee40>"
+        "_abc_impl": "<_abc._abc_data object at 0x7ddf63d9fdc0>"
     },
     "rollout_buffer_kwargs": {},
     "batch_size": 64,
     "n_epochs": 4,
     "clip_range": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWVzAUAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLBUsTQyaVAZcAdAEAAAAAAAAAAAIAiQF8AKsBAAAAAAAAqwEAAAAAAABTAJROhZSMBWZsb2F0lIWUjBJwcm9ncmVzc19yZW1haW5pbmeUhZSMXS9ob21lL250aG9tL21pbmljb25kYTMvZW52cy9ybC9saWIvcHl0aG9uMy4xMi9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMCDxsYW1iZGE+lIwhZ2V0X3NjaGVkdWxlX2ZuLjxsb2NhbHM+LjxsYW1iZGE+lEthQxL4gACkZalO0DtN0yxO0yZPgACUQwCUjA52YWx1ZV9zY2hlZHVsZZSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjF0vaG9tZS9udGhvbS9taW5pY29uZGEzL2VudnMvcmwvbGliL3B5dGhvbjMuMTIvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpRoAIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCN9lH2UKGgaaA+MDF9fcXVhbG5hbWVfX5RoEIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoG4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlGgCKGgHKEsBSwBLAEsBSwVLE0MmlQGXAHQBAAAAAAAAAAACAIkBfACrAQAAAAAAAKsBAAAAAAAAUwCUToWUaAqFlGgMhZSMXS9ob21lL250aG9tL21pbmljb25kYTMvZW52cy9ybC9saWIvcHl0aG9uMy4xMi9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMCDxsYW1iZGE+lIwhZ2V0X3NjaGVkdWxlX2ZuLjxsb2NhbHM+LjxsYW1iZGE+lEthQxL4gACkZalO0DtN0yxO0yZPgACUaBJoE4WUKXSUUpR9lChoGIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulGgajB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUaByMXS9ob21lL250aG9tL21pbmljb25kYTMvZW52cy9ybC9saWIvcHl0aG9uMy4xMi9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oHylSlIWUdJRSlGglaER9lH2UKGgaaDdoKGg4aCl9lGgrTmgsTmgtaD9oLk5oL2gxaAIoaAcoSwFLAEsASwFLAUsTQwiVAZcAiQFTAJRoMymMAV+UhZRoNowEZnVuY5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUS4VDCPiAANgPEogKlGgSjAN2YWyUhZQpdJRSlGg9Tk5oHylSlIWUdJRSlGglaFV9lH2UKGgaaEtoKGhMaCl9lGgrTmgsTmgtaD9oLk5oL2gxRz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjCFlFKUhZRoXF2UaF59lHWGlIZSMIWUUpSFlGhcXZRoXn2UdYaUhlIwLg=="
     },
     "clip_range_vf": null,
     "normalize_advantage": true,

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1b9c8dcd37d6669677cb4b2c0d56e68133be20836cf87e7df483ac924ccc3f2
-size 88362
+oid sha256:4cadb673abae379f996c0b4cdab8ddce0e542bd2f087057f6b719e4f3e7e8569
+size 88490

results.json

@@ -1 +1 @@
-{"mean_reward": 266.3418259, "std_reward": 12.94565794060564, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-31T14:11:33.050083"}
+{"mean_reward": 261.3445663, "std_reward": 17.27037427829461, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-31T14:16:01.751082"}