Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 278.19 +/- 20.07
+      value: 260.19 +/- 37.22
       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 0x10dc2dd30>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x10dc2ddc0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x10dc2de50>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x10dc2dee0>", "_build": "<function ActorCriticPolicy._build at 0x10dc2df70>", "forward": "<function ActorCriticPolicy.forward at 0x10dc31040>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x10dc310d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x10dc31160>", "_predict": "<function ActorCriticPolicy._predict at 0x10dc311f0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x10dc31280>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x10dc31310>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x10dc313a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x10d973380>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1729257181829821000, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.00044800000000000395, "_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": 3908, "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/gAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoC4wCaTiUiYiHlFKUKEsDaA9OTk5K/////0r/////SwB0lGKMCl9ucF9yYW5kb22UTnViLg==", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "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": "macOS-14.5-arm64-arm-64bit Darwin Kernel Version 23.5.0: Wed May  1 20:14:38 PDT 2024; root:xnu-10063.121.3~5/RELEASE_ARM64_T6020", "Python": "3.9.6", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.0", "GPU Enabled": "False", "Numpy": "2.0.2", "Cloudpickle": "3.1.0", "Gymnasium": "0.28.1"}}
+{"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 0x134afc9d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x134afca60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x134afcaf0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x134afcb80>", "_build": "<function ActorCriticPolicy._build at 0x134afcc10>", "forward": "<function ActorCriticPolicy.forward at 0x134afcca0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x134afcd30>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x134afcdc0>", "_predict": "<function ActorCriticPolicy._predict at 0x134afce50>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x134afcee0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x134afcf70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x134aff040>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x134afbe00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1001472, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1729325202814314000, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlgAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAABNRWu9FICiuvNSjrmmOTy0+GuMuqYqozgAAIA/AACAP5SMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsIhpSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlC4="}, "_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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "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": 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": "macOS-14.5-arm64-arm-64bit Darwin Kernel Version 23.5.0: Wed May  1 20:14:38 PDT 2024; root:xnu-10063.121.3~5/RELEASE_ARM64_T6020", "Python": "3.9.6", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.0", "GPU Enabled": "False", "Numpy": "2.0.2", "Cloudpickle": "3.1.0", "Gymnasium": "0.28.1"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f98efca3cc82557ed3522d1f5868473f0c1d28539114afc7a3e0f3182f6d8117
-size 146692
+oid sha256:5ef9d7a3fcf3b2a11892b35a158e234c112dffe99f9b1efe1109a22e8cedc651
+size 146923

ppo-LunarLander-v2/data

@@ -4,32 +4,35 @@
         ":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 0x10dc2dd30>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x10dc2ddc0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x10dc2de50>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x10dc2dee0>",
-        "_build": "<function ActorCriticPolicy._build at 0x10dc2df70>",
-        "forward": "<function ActorCriticPolicy.forward at 0x10dc31040>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x10dc310d0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x10dc31160>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x10dc311f0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x10dc31280>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x10dc31310>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x10dc313a0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x134afc9d0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x134afca60>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x134afcaf0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x134afcb80>",
+        "_build": "<function ActorCriticPolicy._build at 0x134afcc10>",
+        "forward": "<function ActorCriticPolicy.forward at 0x134afcca0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x134afcd30>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x134afcdc0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x134afce50>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x134afcee0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x134afcf70>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x134aff040>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x10d973380>"
+        "_abc_impl": "<_abc._abc_data object at 0x134afbe00>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 1000448,
+    "num_timesteps": 1001472,
     "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1729257181829821000,
+    "start_time": 1729325202814314000,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
-    "_last_obs": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVlgAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAABNRWu9FICiuvNSjrmmOTy0+GuMuqYqozgAAIA/AACAP5SMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsIhpSMAUOUdJRSlC4="
+    },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
         ":serialized:": "gAWVdQAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlC4="
@@ -38,17 +41,17 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.00044800000000000395,
+    "_current_progress_remaining": -0.0014719999999999178,
     "_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": 3908,
+    "_n_updates": 4890,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -66,7 +69,7 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV/gAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoC4wCaTiUiYiHlFKUKEsDaA9OTk5K/////0r/////SwB0lGKMCl9ucF9yYW5kb22UTnViLg==",
+        ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu",
         "n": "4",
         "start": "0",
         "_shape": [],
@@ -74,14 +77,14 @@
         "_np_random": null
     },
     "n_envs": 1,
-    "n_steps": 1024,
+    "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": 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 sha256:38b1792279d9f1e03ea8f55a3d89c529848b718b3da2f7e548ce1ca94e6d3197
+oid sha256:41cca552fcf863bf7b74d6403fa13b1641f9906908af83289622973e01f59821
 size 87978

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c04572124511dcda48b07cbb9b880ac347acb2b79bf6bc46cc42e4356cdaf3e
+oid sha256:522c886c3263156196b288247319804f9a3db4b151499f7a856aaba78f560205
 size 43634

results.json

@@ -1 +1 @@
-{"mean_reward": 278.1932894, "std_reward": 20.07003712133382, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-18T16:32:40.379750"}
+{"mean_reward": 260.1914169, "std_reward": 37.216697167025075, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-19T10:17:30.573161"}