Upload PPO LunarLander-v2 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 296.86 +/- 17.56
+      value: 295.14 +/- 14.94
       name: mean_reward
     task:
       type: reinforcement-learning

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 0x000001C50572FD80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001C50572FE20>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001C50572FEC0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001C50572FF60>", "_build": "<function ActorCriticPolicy._build at 0x000001C505734040>", "forward": "<function ActorCriticPolicy.forward at 0x000001C5057340E0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x000001C505734180>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001C505734220>", "_predict": "<function ActorCriticPolicy._predict at 0x000001C5057342C0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001C505734360>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001C505734400>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001C5057344A0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000001C50509E1C0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 61440, "_total_timesteps": 60000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1687153368575637900, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.02400000000000002, "_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": 73260, "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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 4, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWVsgIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwiVAZcAiQFTAJROhZQpjAFflIWUjHFDOlxVc2Vyc1xMdWNhc0JlcnRvbGFcQXBwRGF0YVxMb2NhbFxQcm9ncmFtc1xQeXRob25cUHl0aG9uMzExXExpYlxzaXRlLXBhY2thZ2VzXHN0YWJsZV9iYXNlbGluZXMzXGNvbW1vblx1dGlscy5weZSMBGZ1bmOUjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlEuEQwj4gADYDxKICpRDAJSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UaAx1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGggfZR9lChoGGgNjAxfX3F1YWxuYW1lX1+UaA6MD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBmMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP8mZmZmZmZqFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="}, "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": "3.11.4", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cpu", "GPU Enabled": "False", "Numpy": "1.25.0", "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 0x0000025878840C20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x0000025878840CC0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x0000025878840D60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x0000025878840E00>", "_build": "<function ActorCriticPolicy._build at 0x0000025878840EA0>", "forward": "<function ActorCriticPolicy.forward at 0x0000025878840F40>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x0000025878840FE0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x0000025878841080>", "_predict": "<function ActorCriticPolicy._predict at 0x0000025878841120>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x00000258788411C0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x0000025878841260>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x0000025878841300>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000002587883D000>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 61440, "_total_timesteps": 60000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1687379327158331600, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.02400000000000002, "_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": 73320, "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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 8, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "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": "Windows-10-10.0.22621-SP0 10.0.22621", "Python": "3.11.4", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.25.0", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e74a2798f0305f5041f0eef20f01b2b3187b5a6c372deb9b2aa3a2fa3986aece
-size 145188
+oid sha256:6f3435e4d044a368d041e1b11e08a5e467e53c0f3bb7f0df73864d537e8f56ef
+size 145825

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 0x000001C50572FD80>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001C50572FE20>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001C50572FEC0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001C50572FF60>",
-        "_build": "<function ActorCriticPolicy._build at 0x000001C505734040>",
-        "forward": "<function ActorCriticPolicy.forward at 0x000001C5057340E0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x000001C505734180>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001C505734220>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x000001C5057342C0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001C505734360>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001C505734400>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001C5057344A0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x0000025878840C20>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x0000025878840CC0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x0000025878840D60>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x0000025878840E00>",
+        "_build": "<function ActorCriticPolicy._build at 0x0000025878840EA0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x0000025878840F40>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x0000025878840FE0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x0000025878841080>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x0000025878841120>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x00000258788411C0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x0000025878841260>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x0000025878841300>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x000001C50509E1C0>"
+        "_abc_impl": "<_abc._abc_data object at 0x000002587883D000>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -26,7 +26,7 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1687153368575637900,
+    "start_time": 1687379327158331600,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": null,
@@ -42,13 +42,13 @@
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 73260,
+    "_n_updates": 73320,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "gAWVdgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=",
@@ -73,7 +73,7 @@
         "dtype": "int64",
         "_np_random": null
     },
-    "n_envs": 4,
+    "n_envs": 8,
     "n_steps": 1024,
     "gamma": 0.999,
     "gae_lambda": 0.98,

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1b81268d1a300756aae521d61f9429acafcaba305cbfd1ec408bf20d27ecb5a
-size 87545
+oid sha256:fd23aaea1fafee30eb208318289e001b43d68ed7e280bf09a2f9d970339c6141
+size 88057

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:789a364d17ba54bde75fa0841ee56d704e8b514103cd1bcfa819b345383b5780
-size 43201
+oid sha256:540e42aaab177575156fa101b4eb5ba0ac315fde9d978663baa0bb3d47ea212d
+size 43329

ppo-LunarLander-v2/system_info.txt

@@ -1,8 +1,8 @@
 - OS: Windows-10-10.0.22621-SP0 10.0.22621
 - Python: 3.11.4
 - Stable-Baselines3: 2.0.0a5
-- PyTorch: 2.0.1+cpu
-- GPU Enabled: False
+- PyTorch: 2.0.1+cu118
+- GPU Enabled: True
 - Numpy: 1.25.0
 - Cloudpickle: 2.2.1
 - Gymnasium: 0.28.1

results.json

@@ -1 +1 @@
-{"mean_reward": 350.85574890000004, "std_reward": 17.559783830507328, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-19T14:50:50.680343"}
+{"mean_reward": 295.14060159999997, "std_reward": 14.942520726844977, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-25T11:29:12.294691"}