Example of PPO in lunar lander

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 268.53 +/- 18.59
+      value: 265.20 +/- 23.34
       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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7f99e58cc280>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f99e58cc310>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f99e58cc3a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f99e58cc430>", "_build": "<function ActorCriticPolicy._build at 0x7f99e58cc4c0>", "forward": "<function ActorCriticPolicy.forward at 0x7f99e58cc550>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f99e58cc5e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f99e58cc670>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f99e58cc700>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f99e58cc790>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f99e58cc820>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f99e58c3ea0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_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": 1669562503351616065, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_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}
+{"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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7fe041216280>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fe041216310>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fe0412163a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fe041216430>", "_build": "<function ActorCriticPolicy._build at 0x7fe0412164c0>", "forward": "<function ActorCriticPolicy.forward at 0x7fe041216550>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fe0412165e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fe041216670>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fe041216700>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fe041216790>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fe041216820>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fe04120eed0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_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": 1669562503351616065, "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-5.15.0-53-generic-x86_64-with-glibc2.29 #59~20.04.1-Ubuntu SMP Thu Oct 20 15:10:22 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu117", "GPU Enabled": "True", "Numpy": "1.23.5", "Gym": "0.21.0"}}

first_test_PPO_LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be3b06cf59e54850bcf9eef501a815e3bf04bcbb6081b095fa3e02c96706955a
-size 147330
+oid sha256:61a820e7690e9435534ced09ab83e132166a979eba9ef27f5545a8c56bf6bc3a
+size 146527

first_test_PPO_LunarLander-v2/data

@@ -4,19 +4,19 @@
         ":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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7f99e58cc280>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f99e58cc310>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f99e58cc3a0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f99e58cc430>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f99e58cc4c0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f99e58cc550>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f99e58cc5e0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f99e58cc670>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f99e58cc700>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f99e58cc790>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f99e58cc820>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fe041216280>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fe041216310>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fe0412163a0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fe041216430>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fe0412164c0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fe041216550>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fe0412165e0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fe041216670>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fe041216700>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fe041216790>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fe041216820>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7f99e58c3ea0>"
+        "_abc_impl": "<_abc_data object at 0x7fe04120eed0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -54,10 +54,7 @@
         ":type:": "<class 'function'>",
         ":serialized:": "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"
     },
-    "_last_obs": {
-        ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
-    },
+    "_last_obs": null,
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
         ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="

first_test_PPO_LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11e314cacb6e148b4f0832bb932ee68cb2747bf09f5b93a742f154c8fb5af0f0
-size 87929
+oid sha256:6a066bb30d8413d4dfd4e216dbef5f65a6efdaa96f1818b70e7ae48bd0874b6f
+size 88057

results.json

@@ -1 +1 @@
-{"mean_reward": 268.53470815101747, "std_reward": 18.592476767705136, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-11-27T12:38:58.632348"}
+{"mean_reward": 265.2035655814244, "std_reward": 23.335833574911067, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-11-27T12:40:01.814540"}