Upload baseline PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 258.98 +/- 18.52
+      value: 253.86 +/- 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 0x7f28da1d9c10>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f28da1d9ca0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f28da1d9d30>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f28da1d9dc0>", "_build": "<function ActorCriticPolicy._build at 0x7f28da1d9e50>", "forward": "<function ActorCriticPolicy.forward at 0x7f28da1d9ee0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f28da1d9f70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f28da1df040>", "_predict": "<function ActorCriticPolicy._predict at 0x7f28da1df0d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f28da1df160>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f28da1df1f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f28da1df280>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f28da1dbcc0>"}, "verbose": 1, "policy_kwargs": {}, "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:": "gAWV9wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1678887866702921130, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOS9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4NDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOS9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "_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, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "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, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "2.0.0a0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.28.0"}}
+{"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 0x7f051067c160>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f051067c1f0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f051067c280>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f051067c310>", "_build": "<function ActorCriticPolicy._build at 0x7f051067c3a0>", "forward": "<function ActorCriticPolicy.forward at 0x7f051067c430>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f051067c4c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f051067c550>", "_predict": "<function ActorCriticPolicy._predict at 0x7f051067c5e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f051067c670>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f051067c700>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f051067c790>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f0510681ec0>"}, "verbose": 1, "policy_kwargs": {}, "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:": "gAWV9wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1678887866702921130, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "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, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "2.0.0a0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.28.0"}}

lunarlander-v2_ppo_v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aab81624293858438b755b36b0f3c4ca5bc9349674bf068a7b1839215beefd9b
-size 145917
+oid sha256:3c1dc45ee132fc0456b7b2dd7e8625515bc0d69522293304c4f1818ad5fdc010
+size 145916

lunarlander-v2_ppo_v0/data

@@ -4,20 +4,20 @@
         ":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 0x7f28da1d9c10>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f28da1d9ca0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f28da1d9d30>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f28da1d9dc0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f28da1d9e50>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f28da1d9ee0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f28da1d9f70>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f28da1df040>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f28da1df0d0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f28da1df160>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f28da1df1f0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f28da1df280>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f051067c160>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f051067c1f0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f051067c280>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f051067c310>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f051067c3a0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f051067c430>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f051067c4c0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f051067c550>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f051067c5e0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f051067c670>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f051067c700>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f051067c790>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f28da1dbcc0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f0510681ec0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -45,7 +45,7 @@
         "dtype": "int64",
         "_np_random": null
     },
-    "n_envs": 16,
+    "n_envs": 1,
     "num_timesteps": 1015808,
     "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,

results.json

@@ -1 +1 @@
-{"mean_reward": 258.98265062935377, "std_reward": 18.51602437736822, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-15T14:14:48.100705"}
+{"mean_reward": 253.864890271422, "std_reward": 21.140961413721673, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-15T14:17:04.399520"}