Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 279.87 +/- 21.91
+      value: 293.96 +/- 12.63
       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 0x79f4ce3a4c10>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79f4ce3a4ca0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79f4ce3a4d30>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79f4ce3a4dc0>", "_build": "<function ActorCriticPolicy._build at 0x79f4ce3a4e50>", "forward": "<function ActorCriticPolicy.forward at 0x79f4ce3a4ee0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x79f4ce3a4f70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79f4ce3a5000>", "_predict": "<function ActorCriticPolicy._predict at 0x79f4ce3a5090>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79f4ce3a5120>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79f4ce3a51b0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x79f4ce3a5240>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x79f4ce345780>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1700758058840678588, "learning_rate": 0.001, "tensorboard_log": null, "_last_obs": null, "_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": -0.015808000000000044, "_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": 496, "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": 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-5.15.120+-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": "2.1.0+cu118", "GPU Enabled": "False", "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 0x786fdfa25fc0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x786fdfa26050>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x786fdfa260e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x786fdfa26170>", "_build": "<function ActorCriticPolicy._build at 0x786fdfa26200>", "forward": "<function ActorCriticPolicy.forward at 0x786fdfa26290>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x786fdfa26320>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x786fdfa263b0>", "_predict": "<function ActorCriticPolicy._predict at 0x786fdfa26440>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x786fdfa264d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x786fdfa26560>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x786fdfa265f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x786fdf9c3700>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1700760684967618081, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_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": -0.007616000000000067, "_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": 1476, "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": 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-5.15.120+-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": "2.1.0+cu118", "GPU Enabled": "False", "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:e9fb2ffc6cd570abebd819257a67791544a22e21d082aaeaf37862243a77dbed
-size 146547
+oid sha256:86f14caeea4e7f9c4df066951609ef788e762c20bc240060e5f62ace82103f55
+size 146545

ppo-LunarLander-v2/data

@@ -4,30 +4,30 @@
         ":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 0x79f4ce3a4c10>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79f4ce3a4ca0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79f4ce3a4d30>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79f4ce3a4dc0>",
-        "_build": "<function ActorCriticPolicy._build at 0x79f4ce3a4e50>",
-        "forward": "<function ActorCriticPolicy.forward at 0x79f4ce3a4ee0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x79f4ce3a4f70>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79f4ce3a5000>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x79f4ce3a5090>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79f4ce3a5120>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79f4ce3a51b0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x79f4ce3a5240>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x786fdfa25fc0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x786fdfa26050>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x786fdfa260e0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x786fdfa26170>",
+        "_build": "<function ActorCriticPolicy._build at 0x786fdfa26200>",
+        "forward": "<function ActorCriticPolicy.forward at 0x786fdfa26290>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x786fdfa26320>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x786fdfa263b0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x786fdfa26440>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x786fdfa264d0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x786fdfa26560>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x786fdfa265f0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x79f4ce345780>"
+        "_abc_impl": "<_abc._abc_data object at 0x786fdf9c3700>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 1015808,
-    "_total_timesteps": 1000000,
+    "num_timesteps": 2015232,
+    "_total_timesteps": 2000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1700758058840678588,
-    "learning_rate": 0.001,
+    "start_time": 1700760684967618081,
+    "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": null,
     "_last_episode_starts": {
@@ -38,17 +38,17 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.015808000000000044,
+    "_current_progress_remaining": -0.007616000000000067,
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWV5QsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHDktq1w5vOMAWyUTQIBjAF0lEdAsD1ZqL0jDHV9lChoBkdAcQESuyNXHWgHS+FoCEdAsD3MzeoDPnV9lChoBkdAcn6O7QLNOmgHTQMBaAhHQLA90iZv1lJ1fZQoaAZHQHLe+VxCIDZoB0vIaAhHQLA95Fd9lVd1fZQoaAZHQG9hx8twrDtoB0vVaAhHQLA+AM/yGzt1fZQoaAZHQHO33L/0dzZoB0vVaAhHQLA+AUAT7EZ1fZQoaAZHQHQGAXMyJsRoB0vvaAhHQLA+Dc8kleF1fZQoaAZHQHOKqy0KJEZoB0v3aAhHQLA+I433pOh1fZQoaAZHQHH5HvH93r5oB0vdaAhHQLA+V2pyZKF1fZQoaAZHQHFRBvm5lOJoB0u2aAhHQLA+b4mkWRB1fZQoaAZHQHDVHvx6OYJoB0vAaAhHQLA+iFvhqCZ1fZQoaAZHQHJ86WHDaXdoB0vlaAhHQLA+zn1WbPR1fZQoaAZHQG6jqC6H0shoB0vWaAhHQLA+0SK3uu11fZQoaAZHQHKU+GXXyy5oB00NAWgIR0CwPtIukDZEdX2UKGgGR0Bxlw+0PYnOaAdL7GgIR0CwPuZc5bQkdX2UKGgGR0Bx7bLaEi+taAdL5mgIR0CwPu2UwBYFdX2UKGgGR0BwenS5RTCMaAdL0mgIR0CwPvGUKRdQdX2UKGgGR0Bui4dMj/uLaAdLxmgIR0CwP0ssDnvEdX2UKGgGR0BxUBH3Dej3aAdL4GgIR0CwP1I7zTWodX2UKGgGR0By9BH7P6bfaAdLyWgIR0CwP1j8LroodX2UKGgGR0Bx2XEzfrKOaAdLxGgIR0CwP2Mbm2b5dX2UKGgGR0ByD4IdELH/aAdL7mgIR0CwP3jAJswddX2UKGgGR0BzYakzoEB9aAdL5GgIR0CwP321+iJwdX2UKGgGR0Bz03ck+otMaAdLvmgIR0CwQr3hsImgdX2UKGgGR0BwoE690zTGaAdLwmgIR0CwQtSKWLP2dX2UKGgGR0BzZonNPgvUaAdNEgFoCEdAsELdx5s0pHV9lChoBkdAcgK92HLzPWgHS71oCEdAsELlqO938nV9lChoBkdAc3UuIyj59GgHS9NoCEdAsEND1Iy0r3V9lChoBkdAcAjkoF3Y+WgHS8VoCEdAsENO7OE/S3V9lChoBkdAcxLAI6bONmgHS+FoCEdAsENXHyVfNXV9lChoBkdAcKcahHskZGgHS95oCEdAsENypIczZnV9lChoBkdAcYAj0cwQDmgHS/ZoCEdAsEN68K5TZXV9lChoBkdAc1JFERaouWgHS+5oCEdAsEOD/zasZHV9lChoBkdAcv17jT8YRGgHS8NoCEdAsEO2OmzjWHV9lChoBkdAcBgEc81XNmgHS8NoCEdAsEO/nA6+4HV9lChoBkdAc6lLHuJDV2gHS9RoCEdAsEPDpxFRYXV9lChoBkdAcvzENOM2nGgHS9NoCEdAsEPw9fTkQ3V9lChoBkdAbdF+VC5VfmgHS9loCEdAsEP1donKGXV9lChoBkdAcqZ7/n4fwWgHS/JoCEdAsEP3n5i3HHV9lChoBkdAcZ/ivPkaM2gHS+NoCEdAsEQMmE4//3V9lChoBkdAcPDxfv4M4WgHS9RoCEdAsEQYu9OARXV9lChoBkdAcUU6be/HpGgHS9JoCEdAsEQeg+Qlr3V9lChoBkdAck8u/Dcdo2gHS9xoCEdAsEQanwXqJXV9lChoBkdAb0pk92X9i2gHS9BoCEdAsER4hzNliHV9lChoBkdAckjoMa0hNmgHS8loCEdAsESAzYVZcXV9lChoBkdAccoyuIRAbGgHS7poCEdAsESLowEhaHV9lChoBkdAc+3nZ00WM2gHS9hoCEdAsESPvmYBvXV9lChoBkdAcbQTQmeDnWgHS+BoCEdAsES9UCJXQ3V9lChoBkdAcQBvEjxCpmgHS79oCEdAsETYMNMGo3V9lChoBkdAcbX4bjtG/mgHS71oCEdAsETZdszl93V9lChoBkdAcW9k1/DtPmgHS85oCEdAsETmEL6UJXV9lChoBkdAcfTL876pHmgHS/doCEdAsETx8+iaiXV9lChoBkdAchiEroW56WgHS61oCEdAsET1vegte3V9lChoBkdAcbDqEeyRjmgHS71oCEdAsEUuLl3hXXV9lChoBkdAbb3UVi4J/2gHS8FoCEdAsEUynhsImnV9lChoBkdAcmH+IdlunGgHS8VoCEdAsEU/U2DQJHV9lChoBkdAcrgHoHLRr2gHS85oCEdAsEU7EVFhHHV9lChoBkdAcq5oWHk92WgHS+VoCEdAsEVCk1uR93V9lChoBkdAcydamoBJZmgHS+toCEdAsEVL0L+glHV9lChoBkdAco29CNS62GgHS7doCEdAsEV6yC4Bm3V9lChoBkdAcnQTBInSfGgHS81oCEdAsEWgUeuFH3V9lChoBkdAcJQXPqs2emgHS99oCEdAsEXI7/4qPXV9lChoBkdAcEU6STyJ9GgHS8hoCEdAsEXwj4YaYXV9lChoBkdAcjxTMJQcgmgHS8VoCEdAsEX55a/yoXV9lChoBkdAcqJe0ojOcGgHS71oCEdAsEX88FINE3V9lChoBkdAcku/n4fwJGgHS8BoCEdAsEX+F10T13V9lChoBkdAcMuvRqoIfWgHTQQBaAhHQLBF//lhgE51fZQoaAZHQHMq4ao/A0toB0vlaAhHQLBGAncL0Bh1fZQoaAZHQHArIwh4dIZoB0vZaAhHQLBGCg9/z8R1fZQoaAZHQHKLKK508vFoB0u9aAhHQLBGOh5PdmB1fZQoaAZHQHLWNwaR6nloB0vfaAhHQLBGX7ALy+Z1fZQoaAZHQHGbQlOXVsloB0vaaAhHQLBGbDUExIt1fZQoaAZHQHMPTwUg0TFoB0vnaAhHQLBGcIpH7P91fZQoaAZHQHFopxNqQBBoB0vvaAhHQLBGhf3vhIh1fZQoaAZHQHHFF4cFQl9oB0vjaAhHQLBGhHyEtd11fZQoaAZHQHKOSmhufmNoB0vSaAhHQLBGohV2icp1fZQoaAZHQHArssDnvDxoB0vLaAhHQLBGv0DU3GZ1fZQoaAZHQHG8PZyuIRBoB0utaAhHQLBG79zOopB1fZQoaAZHQHClnxJ/XoVoB0uyaAhHQLBG8kfcN6R1fZQoaAZHQHHVqaXrt3RoB0u6aAhHQLBHCpuuRtB1fZQoaAZHQHIlOzD4xlBoB0v1aAhHQLBHLrY5DJF1fZQoaAZHQHNhfTLGJepoB0vZaAhHQLBHNol2Ned1fZQoaAZHQHC1wam4y45oB0vlaAhHQLBHS3Tuv2Z1fZQoaAZHQHGmsQEpy6toB0vwaAhHQLBHUDpkf9x1fZQoaAZHQHHFQq/dqL1oB0vHaAhHQLBHY5ksjFB1fZQoaAZHQHJui1E3KjloB0v4aAhHQLBHcwxWT5h1fZQoaAZHQHH5KfnOjZdoB0vBaAhHQLBHjqptJnR1fZQoaAZHQG9/g1m8M/hoB0vPaAhHQLBHnh8pkPN1fZQoaAZHQHE83tv4ubtoB0vfaAhHQLBHqHPeHi51fZQoaAZHQHBsfBeokzJoB0vSaAhHQLBHumtyPuJ1fZQoaAZHQHJrbCJoCdVoB0vjaAhHQLBHz/XXiBJ1fZQoaAZHQHKSo287IT5oB0vLaAhHQLBHzxyn1nN1fZQoaAZHQHA5UhJRO1xoB0vYaAhHQLBH/QyRB/t1fZQoaAZHQHHhMqOLiuNoB0vZaAhHQLBIMkQwsXl1fZQoaAZHQHJnck+otMBoB0vgaAhHQLBIPM/hVEN1fZQoaAZHQHKxIlUp/gBoB0vhaAhHQLBIVRpDeCV1fZQoaAZHQHHwl27nPmhoB0u9aAhHQLBIYQmNR3x1fZQoaAZHQHCgfUONHYpoB0vTaAhHQLBIadBjWkJ1fZQoaAZHQHGtkLUkOZtoB0vbaAhHQLBIcy1NQCV1fZQoaAZHQHI6g2ycCo1oB0vSaAhHQLBIhVQyhzx1ZS4="
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 496,
+    "_n_updates": 1476,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -91,6 +91,6 @@
     "target_kl": null,
     "lr_schedule": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     }
 }

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66460abeeb6f2e959d74752c6cd5a29a4aea7311fee32a283cd99373cb5d1af1
+oid sha256:89b979ddbef4ee4bad9476af0c113a6282e55fdc9452f05bc412c7c5dfd41df1
 size 87978

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d12fadf3dcfeebdd17f85bffd299c4bf92b43cf91da435bc13ceb84e4890f81
+oid sha256:ce07e8402c3f791c97d0d9a224218c9904aada5eb9f7288122576ecd08690c4d
 size 43634

results.json

@@ -1 +1 @@
-{"mean_reward": 279.8742468795158, "std_reward": 21.909221182867455, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-23T17:37:50.900544"}
+{"mean_reward": 293.9588438213816, "std_reward": 12.633849674169594, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-23T18:11:48.583677"}