First commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 95.90 +/- 109.30
+      value: 228.70 +/- 20.68
       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 0x795113728720>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7951137287c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x795113728860>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x795113728900>", "_build": "<function ActorCriticPolicy._build at 0x7951137289a0>", "forward": "<function ActorCriticPolicy.forward at 0x795113728a40>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x795113728ae0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x795113728b80>", "_predict": "<function ActorCriticPolicy._predict at 0x795113728c20>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x795113728cc0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x795113728d60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x795113728e00>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7951136abc80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1048576, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1722708643070641059, "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:": "gAWV8wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAABAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYkuAhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.04857599999999995, "_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": 4, "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": 128, "n_steps": 8192, "gamma": 0.99, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 256, "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-6.8.0-39-lowlatency-x86_64-with-glibc2.35 # 39.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 16 14:55:32 UTC 2024", "Python": "3.11.0rc1", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.4.0+cu121", "GPU Enabled": "True", "Numpy": "1.23.1", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.1"}}
+{"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 0x795113728720>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7951137287c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x795113728860>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x795113728900>", "_build": "<function ActorCriticPolicy._build at 0x7951137289a0>", "forward": "<function ActorCriticPolicy.forward at 0x795113728a40>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x795113728ae0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x795113728b80>", "_predict": "<function ActorCriticPolicy._predict at 0x795113728c20>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x795113728cc0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x795113728d60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x795113728e00>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7951136abc80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 13312, "_total_timesteps": 10000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1722711753787648289, "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:": "gAWV8wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYkuAhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.44949760000000005, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 84, "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": 128, "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": 512, "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-6.8.0-39-lowlatency-x86_64-with-glibc2.35 # 39.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 16 14:55:32 UTC 2024", "Python": "3.11.0rc1", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.4.0+cu121", "GPU Enabled": "True", "Numpy": "1.23.1", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.1"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a84f48fbd748bab36b1233336734c766220582b0a5be1d0496e9219c8e691f7
-size 152850
+oid sha256:7fa4bac13af999802e966d5725488faab338054308204c42a2bf65718ce9791c
+size 148842

ppo-LunarLander-v2/data

@@ -21,37 +21,37 @@
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 1048576,
-    "_total_timesteps": 1000000,
+    "num_timesteps": 13312,
+    "_total_timesteps": 10000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1722708643070641059,
+    "start_time": 1722711753787648289,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWV8wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAABAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYkuAhZSMAUOUdJRSlC4="
+        ":serialized:": "gAWV8wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYkuAhZSMAUOUdJRSlC4="
     },
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.04857599999999995,
+    "_current_progress_remaining": 0.44949760000000005,
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 4,
+    "_n_updates": 84,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -77,14 +77,14 @@
         "_np_random": null
     },
     "n_envs": 128,
-    "n_steps": 8192,
-    "gamma": 0.99,
+    "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": 256,
-    "n_epochs": 4,
+    "batch_size": 512,
+    "n_epochs": 2,
     "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 sha256:40a4294a40e63427e4d333460febb1d14a66fd96ee4b5ac3ead8b9086d958492
+oid sha256:45d4ba37bf8a9fb8e58477572f3e360476ea10c5e0a615f232b1d49c34b1142f
 size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3de259d9e8e48577dbc49b3c09d8b166c8ee74a0f975d3002db4bca1f189023a
+oid sha256:444d37ad54809ce8a1aae81cbebee3f9f18a2b10623019b1a9949faefd85b93d
 size 43762

results.json

@@ -1 +1 @@
-{"mean_reward": 95.89520569999999, "std_reward": 109.3034368441561, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-03T18:12:21.678337"}
+{"mean_reward": 228.6968485, "std_reward": 20.679376484097126, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-03T19:02:57.537697"}