v4

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 189.27 +/- 104.73
+      value: 237.47 +/- 21.14
       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 0x73c2c58e5b40>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x73c2c58e5bd0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x73c2c58e5c60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x73c2c58e5cf0>", "_build": "<function ActorCriticPolicy._build at 0x73c2c58e5d80>", "forward": "<function ActorCriticPolicy.forward at 0x73c2c58e5e10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x73c2c58e5ea0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x73c2c58e5f30>", "_predict": "<function ActorCriticPolicy._predict at 0x73c2c58e5fc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x73c2c58e6050>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x73c2c58e60e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x73c2c58e6170>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x73c2cc66a200>"}, "verbose": 0, "policy_kwargs": {}, "num_timesteps": 1007616, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1736280234426030861, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV9gAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWgAAAAAAAAAAzNGi+m0YNPyHFu7zsC8i+naeKveJKdz0AAAAAAAAAAMCyqD4EOAU/PXH3vY6+vr7bSNQ84KSOvgAAAAAAAAAApsHnPT95bD8dEGk+KXLYvqehWzvHMK08AAAAAAAAAADAl+Q9rhGQumQ7J71Hd8i10BipOkiPNjUAAAAAAACAP5SMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLBEsIhpSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVeAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWBAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksEhZSMAUOUdJRSlC4="}, "_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": 246, "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": 4, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.989, "ent_coef": 0.009, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 2, "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-6.8.0-1017-azure-x86_64-with-glibc2.35 # 20~22.04.1-Ubuntu SMP Tue Oct 22 20:42:07 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.1+cu124", "GPU Enabled": "True", "Numpy": "2.2.1", "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 0x7d42cd6d63b0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d42cd6d6440>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d42cd6d64d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d42cd6d6560>", "_build": "<function ActorCriticPolicy._build at 0x7d42cd6d65f0>", "forward": "<function ActorCriticPolicy.forward at 0x7d42cd6d6680>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d42cd6d6710>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d42cd6d67a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7d42cd6d6830>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d42cd6d68c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d42cd6d6950>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d42cd6d69e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d42f2e4ba00>"}, "verbose": 0, "policy_kwargs": {"net_arch": [64, 64]}, "num_timesteps": 1001472, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1736299251695343848, "learning_rate": 0.001, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVfAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUjAFDlHSUUpQu"}, "_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": 1956, "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": 8, "n_steps": 256, "gamma": 0.999, "gae_lambda": 0.99, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "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-6.8.0-1018-azure-x86_64-with-glibc2.35 # 21~22.04.1-Ubuntu SMP Fri Nov  8 00:21:25 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.1+cu124", "GPU Enabled": "True", "Numpy": "2.2.1", "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 sha256:10a99153f034c31a35e6f500f0fa9ad4ccf955844cbf89b5ad1c6e95913d4aa0
-size 147571
+oid sha256:306d95a39782e453f638f4d35749e45f6e626f0ba343e805240643d34514467e
+size 147798

ppo-LunarLander-v2/data

@@ -4,54 +4,59 @@
         ":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 0x73c2c58e5b40>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x73c2c58e5bd0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x73c2c58e5c60>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x73c2c58e5cf0>",
-        "_build": "<function ActorCriticPolicy._build at 0x73c2c58e5d80>",
-        "forward": "<function ActorCriticPolicy.forward at 0x73c2c58e5e10>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x73c2c58e5ea0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x73c2c58e5f30>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x73c2c58e5fc0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x73c2c58e6050>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x73c2c58e60e0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x73c2c58e6170>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7d42cd6d63b0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d42cd6d6440>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d42cd6d64d0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d42cd6d6560>",
+        "_build": "<function ActorCriticPolicy._build at 0x7d42cd6d65f0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7d42cd6d6680>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d42cd6d6710>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d42cd6d67a0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7d42cd6d6830>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d42cd6d68c0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d42cd6d6950>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d42cd6d69e0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x73c2cc66a200>"
+        "_abc_impl": "<_abc._abc_data object at 0x7d42f2e4ba00>"
     },
     "verbose": 0,
-    "policy_kwargs": {},
-    "num_timesteps": 1007616,
+    "policy_kwargs": {
+        "net_arch": [
+            64,
+            64
+        ]
+    },
+    "num_timesteps": 1001472,
     "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1736280234426030861,
-    "learning_rate": 0.0003,
+    "start_time": 1736299251695343848,
+    "learning_rate": 0.001,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWV9gAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWgAAAAAAAAAAzNGi+m0YNPyHFu7zsC8i+naeKveJKdz0AAAAAAAAAAMCyqD4EOAU/PXH3vY6+vr7bSNQ84KSOvgAAAAAAAAAApsHnPT95bD8dEGk+KXLYvqehWzvHMK08AAAAAAAAAADAl+Q9rhGQumQ7J71Hd8i10BipOkiPNjUAAAAAAACAP5SMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLBEsIhpSMAUOUdJRSlC4="
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVeAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWBAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksEhZSMAUOUdJRSlC4="
+        ":serialized:": "gAWVfAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUjAFDlHSUUpQu"
     },
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.007616000000000067,
+    "_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": 246,
+    "_n_updates": 1956,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -69,22 +74,22 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV/gAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoC4wCaTiUiYiHlFKUKEsDaA9OTk5K/////0r/////SwB0lGKMCl9ucF9yYW5kb22UTnViLg==",
+        ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu",
         "n": "4",
         "start": "0",
         "_shape": [],
         "dtype": "int64",
         "_np_random": null
     },
-    "n_envs": 4,
-    "n_steps": 2048,
-    "gamma": 0.99,
-    "gae_lambda": 0.989,
-    "ent_coef": 0.009,
+    "n_envs": 8,
+    "n_steps": 256,
+    "gamma": 0.999,
+    "gae_lambda": 0.99,
+    "ent_coef": 0.0,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
-    "batch_size": 64,
-    "n_epochs": 2,
+    "batch_size": 128,
+    "n_epochs": 4,
     "clip_range": {
         ":type:": "<class 'function'>",
         ":serialized:": "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"
@@ -94,6 +99,6 @@
     "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:e8e9fe89de27b1806d958ab4a2ca91874c8a83d300f1a53170b14cc32ac636fc
+oid sha256:74c16db01519716f83dbadc5b0922f888a08d022613a8d39edb265112f1f79d5
 size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d2dd51ad15211e4aaf78ecd05745379f4e40ae4bd762e6e3007c7fe85396233
+oid sha256:6afe12db7b8de57bd7404b30c362c697af3372cf4759579a1c39f9c45023e183
 size 43762

ppo-LunarLander-v2/system_info.txt

@@ -1,4 +1,4 @@
-- OS: Linux-6.8.0-1017-azure-x86_64-with-glibc2.35 # 20~22.04.1-Ubuntu SMP Tue Oct 22 20:42:07 UTC 2024
+- OS: Linux-6.8.0-1018-azure-x86_64-with-glibc2.35 # 21~22.04.1-Ubuntu SMP Fri Nov  8 00:21:25 UTC 2024
 - Python: 3.10.12
 - Stable-Baselines3: 2.0.0a5
 - PyTorch: 2.5.1+cu124

results.json

@@ -1 +1 @@
-{"mean_reward": 189.26988857336454, "std_reward": 104.73322987841847, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-07T20:14:45.087193"}
+{"mean_reward": 237.46547742037765, "std_reward": 21.139508824368217, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-08T01:30:36.537922"}