double batch, epochs, steps, timesteps

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 288.87 +/- 19.10
+      value: 293.70 +/- 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 0x7efb606970a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7efb60697130>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7efb606971c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7efb60697250>", "_build": "<function ActorCriticPolicy._build at 0x7efb606972e0>", "forward": "<function ActorCriticPolicy.forward at 0x7efb60697370>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7efb60697400>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7efb60697490>", "_predict": "<function ActorCriticPolicy._predict at 0x7efb60697520>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7efb606975b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7efb60697640>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7efb606976d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7efb6b39c600>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 0, "_total_timesteps": 5000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1688253407070439212, "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": -0.004885333333333408, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1480, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "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", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 16, "n_steps": 2048, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "n_epochs": 8, "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-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "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 0x7efb606970a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7efb60697130>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7efb606971c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7efb60697250>", "_build": "<function ActorCriticPolicy._build at 0x7efb606972e0>", "forward": "<function ActorCriticPolicy.forward at 0x7efb60697370>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7efb60697400>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7efb60697490>", "_predict": "<function ActorCriticPolicy._predict at 0x7efb60697520>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7efb606975b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7efb60697640>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7efb606976d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7efb6b39c600>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 5013504, "_total_timesteps": 5000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1688253518883838365, "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": -0.0027007999999999477, "_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": 1224, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 2048, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "n_epochs": 8, "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-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2-005.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ee1da41254f0ce04cc5bf36b1c06e4b1e1d50e597a1a3ef737a1e434f7590a3
+size 146630

ppo-LunarLander-v2-005/_stable_baselines3_version

@@ -0,0 +1 @@
+2.0.0a5

ppo-LunarLander-v2-005/data

@@ -0,0 +1,99 @@
+{
+    "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 0x7efb606970a0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7efb60697130>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7efb606971c0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7efb60697250>",
+        "_build": "<function ActorCriticPolicy._build at 0x7efb606972e0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7efb60697370>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7efb60697400>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7efb60697490>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7efb60697520>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7efb606975b0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7efb60697640>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7efb606976d0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7efb6b39c600>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 5013504,
+    "_total_timesteps": 5000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1688253518883838365,
+    "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": -0.0027007999999999477,
+    "_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": 1224,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True  True  True]",
+        "_shape": [
+            8
+        ],
+        "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]",
+        "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]",
+        "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]",
+        "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "n_steps": 2048,
+    "gamma": 0.999,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.01,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 128,
+    "n_epochs": 8,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

ppo-LunarLander-v2-005/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbf5dbf001b8ebba06255b9d45f8477650448d0c981d35a2e10efb5116c77fec
+size 87929

ppo-LunarLander-v2-005/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cbf51b0811fbf980bcad3f8ea322e50b81c380a353c80e22181aeae802ffb34
+size 43329

ppo-LunarLander-v2-005/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

ppo-LunarLander-v2-005/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.0.1+cu118
+- GPU Enabled: True
+- Numpy: 1.22.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -1 +1 @@
-{"mean_reward": 288.87060790000004, "std_reward": 19.095685792317067, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-01T23:17:06.754472"}
+{"mean_reward": 293.6966756, "std_reward": 20.04629264708437, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-02T00:32:48.641682"}