Trained model

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -1287.04 +/- 1096.56
+      value: 291.52 +/- 22.96
       name: mean_reward
     task:
       type: reinforcement-learning

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 0x7fc88b367ca0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc88b367d30>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc88b367dc0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc88b367e50>", "_build": "<function ActorCriticPolicy._build at 0x7fc88b367ee0>", "forward": "<function ActorCriticPolicy.forward at 0x7fc88b367f70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc88b36a040>", "_predict": "<function ActorCriticPolicy._predict at 0x7fc88b36a0d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc88b36a160>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc88b36a1f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc88b36a280>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fc88b363e00>"}, "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": 16384, "_total_timesteps": 10000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652260831.130133, "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": -0.6384000000000001, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 4, "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-5.15.0-27-generic-x86_64-with-glibc2.35 #28-Ubuntu SMP Thu Apr 14 04:55:28 UTC 2022", "Python": "3.9.12", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.22.3", "Gym": "0.21.0"}}
+{"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 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 0x7f11a7126d30>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f11a7126dc0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f11a7126e50>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f11a7126ee0>", "_build": "<function ActorCriticPolicy._build at 0x7f11a7126f70>", "forward": "<function ActorCriticPolicy.forward at 0x7f11a7129040>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f11a71290d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f11a7129160>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f11a71291f0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f11a7129280>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f11a7129310>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f11a71d9c00>"}, "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": 1652239800.1165988, "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": 524, "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-5.15.0-27-generic-x86_64-with-glibc2.35 #28-Ubuntu SMP Thu Apr 14 04:55:28 UTC 2022", "Python": "3.9.12", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.22.3", "Gym": "0.21.0"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c44788c5bd2c6d3fec99891e30d17bbb3eecf82d38ba648aa9e6c0e72c76bc4
+oid sha256:4df81992fe6dcb5619666c6a919b40a72985a7f85838ac0d6c67aae75db99901
 size 144118

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 0x7fee14dd51f0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fee14dd5280>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fee14dd5310>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fee14dd53a0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7fee14dd5430>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7fee14dd54c0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fee14dd5550>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7fee14dd55e0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fee14dd5670>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fee14dd5700>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fee14dd5790>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f11a7126d30>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f11a7126dc0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f11a7126e50>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f11a7126ee0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f11a7126f70>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f11a7129040>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f11a71290d0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f11a7129160>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f11a71291f0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f11a7129280>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f11a7129310>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7fee14ede280>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f11a71d9c00>"
     },
     "verbose": 1,
     "policy_kwargs": {},

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1001c75763c6f065ee824c804d1f8945ab1fa98f9ae730dd9ad07d5cbbba949
-size 91062
+oid sha256:7e2dc0948115c6f920d7afc91205a34bfc57310de5fa4c38553b813d83d39503
+size 198733

results.json

@@ -1 +1 @@
-{"mean_reward": -1287.040195265971, "std_reward": 1096.5638487125193, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T11:20:55.772931"}
+{"mean_reward": 291.5160401400264, "std_reward": 22.960656766607634, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T11:39:24.310293"}