Second commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -150.39 +/- 54.21
+      value: 250.37 +/- 33.48
       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 0x7d5e831c95a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d5e831c9630>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d5e831c96c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d5e831c9750>", "_build": "<function ActorCriticPolicy._build at 0x7d5e831c97e0>", "forward": "<function ActorCriticPolicy.forward at 0x7d5e831c9870>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d5e831c9900>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d5e831c9990>", "_predict": "<function ActorCriticPolicy._predict at 0x7d5e831c9a20>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d5e831c9ab0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d5e831c9b40>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d5e831c9bd0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d5ee192a880>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 114688, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1695115723108484902, "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": -0.1468799999999999, "_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": 28, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "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": 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": "Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "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 0x7fbd731c3370>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fbd731c3400>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fbd731c3490>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fbd731c3520>", "_build": "<function ActorCriticPolicy._build at 0x7fbd731c35b0>", "forward": "<function ActorCriticPolicy.forward at 0x7fbd731c3640>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fbd731c36d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fbd731c3760>", "_predict": "<function ActorCriticPolicy._predict at 0x7fbd731c37f0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fbd731c3880>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fbd731c3910>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fbd731c39a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fbd740b56c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1001472, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1695292104428431356, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAJquxTx6F7M/eZScPY8Awr5njku8dsgCPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.0014719999999999178, "_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": 4890, "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": 1, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "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": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "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 sha256:6dfaaf68b1fa9841bda41aacb3427184a3634c0a8b7ada14264931763e76590b
-size 146621
+oid sha256:6c67f8301a61afae55d98303cd79ca26df163b0dd57e24dfc9a0488091ef9743
+size 146023

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 0x7d5e831c95a0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d5e831c9630>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d5e831c96c0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d5e831c9750>",
-        "_build": "<function ActorCriticPolicy._build at 0x7d5e831c97e0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7d5e831c9870>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d5e831c9900>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d5e831c9990>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7d5e831c9a20>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d5e831c9ab0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d5e831c9b40>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d5e831c9bd0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fbd731c3370>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fbd731c3400>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fbd731c3490>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fbd731c3520>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fbd731c35b0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fbd731c3640>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fbd731c36d0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fbd731c3760>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fbd731c37f0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fbd731c3880>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fbd731c3910>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fbd731c39a0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7d5ee192a880>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fbd740b56c0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 114688,
-    "_total_timesteps": 100000,
+    "num_timesteps": 1001472,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1695115723108484902,
+    "start_time": 1695292104428431356,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAJquxTx6F7M/eZScPY8Awr5njku8dsgCPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
     },
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.1468799999999999,
+    "_current_progress_remaining": -0.0014719999999999178,
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWV4gsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwEWZuNxVAA2MAWyUS06MAXSUR0ChQ/un2qT9dX2UKGgGR8BLw7sWweNlaAdLXmgIR0ChRAtutOmBdX2UKGgGR8A7HMiKR+z/aAdLVWgIR0ChRCPNVzZIdX2UKGgGR8BLgvGZNO/MaAdLV2gIR0ChRCtYjjaPdX2UKGgGR8A4HMnqmj0uaAdLkmgIR0ChRDjDjzZpdX2UKGgGR8BDuue8PFvRaAdLc2gIR0ChRD7SiM5wdX2UKGgGR8AEackMTewcaAdLf2gIR0ChREoHC4z8dX2UKGgGR8BQwyde6ZpjaAdLgmgIR0ChRIxDTjNqdX2UKGgGR8BER/mcOLBLaAdLcGgIR0ChRMGnXNC7dX2UKGgGR8AcqjCYTj//aAdLXmgIR0ChRM8wQDmsdX2UKGgGR8BQOS88La24aAdLZ2gIR0ChRM2tEG7jdX2UKGgGR8BBWCYLLIPtaAdLVWgIR0ChRNDqv/zbdX2UKGgGR8BUXf+S8rZraAdLbmgIR0ChRNhMJx//dX2UKGgGR8BJiBDohY/3aAdLYWgIR0ChRNT06HTJdX2UKGgGR8BCu8Emplz2aAdLSWgIR0ChRPWPLgXNdX2UKGgGR8BUeN6ol2NeaAdLZWgIR0ChRQL/82rGdX2UKGgGR8BIP4ODrZ8KaAdLZmgIR0ChRQTRIBikdX2UKGgGR7/nzuF6AvtdaAdLVmgIR0ChRQmu9vjwdX2UKGgGR8A0cIIWxhUjaAdLcmgIR0ChRU2YfGModX2UKGgGR8BBhQCCBf8eaAdLRmgIR0ChRZP1lGwzdX2UKGgGR8BJPQmE4//vaAdLaWgIR0ChRawM6RyPdX2UKGgGR8A2JAVfu1F6aAdLjmgIR0ChRb1Jtix3dX2UKGgGR8AQtfWtlqagaAdLjWgIR0ChRchjWkJsdX2UKGgGR8A4y9zfaYeDaAdLSGgIR0ChRdDaXa8IdX2UKGgGR8A/eHJ9y926aAdLUmgIR0ChReyLAHmjdX2UKGgGR8BR67eVLSNPaAdLWWgIR0ChRfJIczZZdX2UKGgGR8BJPdO6/ZdwaAdLbGgIR0ChRfE1/DtPdX2UKGgGR8BZc1PnB+F2aAdLa2gIR0ChRfpQ1rIpdX2UKGgGR8BOlqBEroW6aAdLeWgIR0ChRiMvh60IdX2UKGgGR8BR6C925hBraAdLf2gIR0ChRjK7iADrdX2UKGgGR8AmOKIi1RceaAdLf2gIR0ChRjwevIOpdX2UKGgGR8BCPbDdgv12aAdLVWgIR0ChRkQrlNlAdX2UKGgGR8BL0adlNDc/aAdLcGgIR0ChRkflp48mdX2UKGgGR8BXiw0waisXaAdLVmgIR0ChRoh6jWTYdX2UKGgGR8BSJfkJa7mMaAdLa2gIR0ChRt4k/r0KdX2UKGgGR8BQVX9BKL88aAdLW2gIR0ChRvziS7oTdX2UKGgGR8BMhnF5v99/aAdLaWgIR0ChRv+Vkc0cdX2UKGgGR8BF5xF7Uoa2aAdLSGgIR0ChRxY5ksjFdX2UKGgGR8At5ky1uzhQaAdLXmgIR0ChRzg2ycCpdX2UKGgGR8ASzXjENvwWaAdLgGgIR0ChRzWXb/OudX2UKGgGR8BUTrTlT3qSaAdLc2gIR0ChR0F/x2B8dX2UKGgGR8BgD29tdiUgaAdNKwFoCEdAoUdUbaRISXV9lChoBkfAVlwXTEzfrWgHS1toCEdAoUdZTyauwHV9lChoBkfARKBJ04iosWgHS4hoCEdAoUdbH+6y0XV9lChoBkfASnRH5JsfrGgHS4VoCEdAoUdzMJQcgnV9lChoBkfAVCtBAv+OwWgHS3BoCEdAoUeCBXjlxXV9lChoBkfAU8yso2GZeGgHS4xoCEdAoUeQg/1QInV9lChoBkdAIEfpMYdhiWgHS31oCEdAoUewTRIBinV9lChoBkfAQCWNR3u/lGgHS05oCEdAoUfNVmz0H3V9lChoBkfAUBbTYukDZGgHS0hoCEdAoUfZCx/us3V9lChoBkfAUYwPxx1gY2gHS3RoCEdAoUfljZtelnV9lChoBkfAUHMEGJN0vGgHS05oCEdAoUgaOgg5inV9lChoBkfAQbNSZSeiBWgHS1doCEdAoUgaHVPN3XV9lChoBkfAQH2jXWe6I2gHS1hoCEdAoUhV4/u9e3V9lChoBkfAUbTNqxkd3mgHS2NoCEdAoUhdLzwtrnV9lChoBkfARqGfqX4TK2gHS1poCEdAoUhinFYMfHV9lChoBkfAU9yyLQ5WBGgHS09oCEdAoUh1m+TNdXV9lChoBkfAWUaeWfK6nWgHS41oCEdAoUiil+EytXV9lChoBkfAQHC7VawD/2gHS1JoCEdAoUigVj7Q9nV9lChoBkfAMcnZPEbYLGgHS0toCEdAoUjDpX6qKnV9lChoBkfAWQR90A93bGgHS3JoCEdAoUjOkP+XJHV9lChoBkfAVch0dRzij2gHS4ZoCEdAoUjNJYkmhXV9lChoBkfAUDHQkX1rZmgHS3loCEdAoUjX/95yEXV9lChoBkfARevnIQvpQmgHS4FoCEdAoUjUn5SFXnV9lChoBkfAT8dNcnmaIGgHS29oCEdAoUknHNorWnV9lChoBkfASIS+Yc/+sGgHS19oCEdAoUk7Fn7HhnV9lChoBkfASZrbDdgv12gHS05oCEdAoUlLEk0JnnV9lChoBkfAXPEVARkEtGgHS4ZoCEdAoUlhOFg2InV9lChoBkfASn39m6GxlmgHS3ZoCEdAoUmNcB2fTXV9lChoBkfARND6k690zWgHS2ZoCEdAoUmfthNM5HV9lChoBkfAQN9NSIgvDmgHS0xoCEdAoUne6PKdQXV9lChoBkfAWIgVh1DBuWgHS3doCEdAoUn+RmseXHV9lChoBkfAQ86QvHtF8WgHS2NoCEdAoUoFl/Yra3V9lChoBkfAWdggHNX5nGgHS2hoCEdAoUoY9RrJsHV9lChoBkfAXb5oZhrnDGgHS3poCEdAoUolOO8013V9lChoBkfAN9oouwosqmgHS19oCEdAoUpACMglnnV9lChoBkfAV+XiNsFdLWgHS2poCEdAoUpiquKXOXV9lChoBkfAUbpN47ihnWgHS2xoCEdAoUpgHeJpFnV9lChoBkfASPakwevIO2gHS1toCEdAoUqaoddVvXV9lChoBkfARnmLP2PDHmgHS1VoCEdAoUqvSSeRP3V9lChoBkfAWEVXjlxOtWgHS1poCEdAoUqxxYJVsHV9lChoBkfAWKjxCpm29mgHS2toCEdAoUsuwcHW0HV9lChoBkfASb3+VC5VfmgHS05oCEdAoUsxCSidrnV9lChoBkfAUg1W912aD2gHS2FoCEdAoUtIJJGvwHV9lChoBkfAQTCbYsd1dWgHS2xoCEdAoUtnqgRK6HV9lChoBkfAVPyFajesP2gHS2FoCEdAoUuqpWFN+XV9lChoBkfAU7IsFt8/lmgHS05oCEdAoUu9QO4G2XV9lChoBkdAQdz/XGwRoWgHTegDaAhHQKFLyrupjtp1fZQoaAZHwFIZhEBsANpoB0tWaAhHQKFL3jPOY6Z1fZQoaAZHwFPgfV7Qb+9oB0t+aAhHQKFMK4Nqgyx1fZQoaAZHwFWQZmZmZmZoB0thaAhHQKFMMIUJv5x1fZQoaAZHwEGGMVDa4+doB0uJaAhHQKFMQmbb1yx1fZQoaAZHwDPgcNpdrwhoB0uJaAhHQKFMWYXwb2l1fZQoaAZHwFxI3Zf2K2toB0uLaAhHQKFMc7/4qPR1fZQoaAZHwDHjkCFK02NoB0tWaAhHQKFMfF0gbId1fZQoaAZHwER24dZJTVFoB0teaAhHQKFMlH5Jsft1fZQoaAZHwFQcEoOQQtloB0tjaAhHQKFMt4Oc2BJ1fZQoaAZHwC2xdIGyHEdoB0tKaAhHQKFMthVENON1fZQoaAZHwCLMd7v5P/JoB0uMaAhHQKFM0TZg5R11fZQoaAZHwE2XR3u/k/9oB0umaAhHQKFNKTbnHNp1ZS4="
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 28,
+    "_n_updates": 4890,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -76,15 +76,15 @@
         "dtype": "int64",
         "_np_random": null
     },
-    "n_envs": 16,
-    "n_steps": 1024,
-    "gamma": 0.999,
-    "gae_lambda": 0.98,
-    "ent_coef": 0.01,
+    "n_envs": 1,
+    "n_steps": 2048,
+    "gamma": 0.99,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.0,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
     "batch_size": 64,
-    "n_epochs": 4,
+    "n_epochs": 10,
     "clip_range": {
         ":type:": "<class 'function'>",
         ":serialized:": "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"

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffbc3ea86edc487f2473a364bb0e01582eb6e2409a42a9d134be014e571086d2
+oid sha256:858b936441fb930168358c863b0c8ea75d2b4514eb620da089250f0653bce1ce
 size 87929

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bc2754a5b7d7403504c357509d03ccb404cec3e09f3d5ede681eda4547ca71b
+oid sha256:64c73cf2b34f7839d2960d958fc92e6b8b17142825a6be28697d10bd6c39e824
 size 43329

ppo-LunarLander-v2/system_info.txt

@@ -1,4 +1,4 @@
-- OS: Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023
+- OS: Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023
 - Python: 3.10.12
 - Stable-Baselines3: 2.0.0a5
 - PyTorch: 2.0.1+cu118

results.json

@@ -1 +1 @@
-{"mean_reward": -150.3886627, "std_reward": 54.211501033139264, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-19T09:43:08.374192"}
+{"mean_reward": 250.3743414, "std_reward": 33.48127265222457, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-21T11:17:39.526429"}