Upload of a PPO trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 255.41 +/- 24.30
+      value: 232.46 +/- 51.12
       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 0x7f880f6252d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f880f625360>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f880f6253f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f880f625480>", "_build": "<function ActorCriticPolicy._build at 0x7f880f625510>", "forward": "<function ActorCriticPolicy.forward at 0x7f880f6255a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f880f625630>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f880f6256c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f880f625750>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f880f6257e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f880f625870>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f880f625900>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f880f5c1100>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1719438317705329596, "learning_rate": 0.0003, "tensorboard_log": null, "_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, "_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": 248, "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/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Fri May 24 14:06:39 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0+cu121", "GPU Enabled": "False", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
+{"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 0x7cbc6696ac20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7cbc6696acb0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7cbc6696ad40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7cbc6696add0>", "_build": "<function ActorCriticPolicy._build at 0x7cbc6696ae60>", "forward": "<function ActorCriticPolicy.forward at 0x7cbc6696aef0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7cbc6696af80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7cbc6696b010>", "_predict": "<function ActorCriticPolicy._predict at 0x7cbc6696b0a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7cbc6696b130>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7cbc6696b1c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7cbc6696b250>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7cbc6690f000>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1719438317705329596, "learning_rate": 0.0003, "tensorboard_log": null, "_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, "_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": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVdgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "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/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Fri May 24 14:06:39 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0+cu121", "GPU Enabled": "False", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8990bbd5dc1abd21bc6978fdfdb62411c79c62a7bd369e0fd6b7467177b6153
+oid sha256:5a93d6ac8aa088a40f059356ba73054a5d2f94259c3542317d577e578cacff31
 size 146686

ppo-LunarLander-v2/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 0x7f880f6252d0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f880f625360>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f880f6253f0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f880f625480>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f880f625510>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f880f6255a0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f880f625630>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f880f6256c0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f880f625750>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f880f6257e0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f880f625870>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f880f625900>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7cbc6696ac20>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7cbc6696acb0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7cbc6696ad40>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7cbc6696add0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7cbc6696ae60>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7cbc6696aef0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7cbc6696af80>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7cbc6696b010>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7cbc6696b0a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7cbc6696b130>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7cbc6696b1c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7cbc6696b250>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f880f5c1100>"
+        "_abc_impl": "<_abc._abc_data object at 0x7cbc6690f000>"
     },
     "verbose": 1,
     "policy_kwargs": {},

results.json

@@ -1 +1 @@
-{"mean_reward": 255.4077028, "std_reward": 24.297545288284905, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-26T22:29:54.910105"}
+{"mean_reward": 232.4576571, "std_reward": 51.11560086464742, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-26T22:36:08.655607"}