Upload PPO Pendulum-v1 trained agent
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-Pendulum-v1.zip +2 -2
- ppo-Pendulum-v1/_stable_baselines3_version +1 -1
- ppo-Pendulum-v1/data +25 -41
- ppo-Pendulum-v1/policy.optimizer.pth +2 -2
- ppo-Pendulum-v1/policy.pth +2 -2
- ppo-Pendulum-v1/system_info.txt +3 -3
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: Pendulum-v1
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value: -
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: Pendulum-v1
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: -421.52 +/- 342.09
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
config.json
CHANGED
@@ -1 +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 0x79ae83617520>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79ae836175b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79ae83617640>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79ae836176d0>", "_build": "<function ActorCriticPolicy._build at 0x79ae83617760>", "forward": "<function ActorCriticPolicy.forward at 0x79ae836177f0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x79ae83617880>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79ae83617910>", "_predict": "<function ActorCriticPolicy._predict at 0x79ae836179a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79ae83617a30>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79ae83617ac0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x79ae83617b50>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x79ae8361d180>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 100352, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1722880280815447130, "learning_rate": 0.001, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYMAAAAAAAAADf37D5q7mK/ib6mQJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsDhpSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": true, "sde_sample_freq": 4, "_current_progress_remaining": -0.0035199999999999676, "_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": 490, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True]", "bounded_above": "[ True True True]", "_shape": [3], "low": "[-1. -1. -8.]", "high": "[1. 1. 8.]", "low_repr": "[-1. -1. -8.]", "high_repr": "[1. 1. 8.]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True]", "bounded_above": "[ True]", "_shape": [1], "low": "[-2.]", "high": "[2.]", "low_repr": "-2.0", "high_repr": "2.0", "_np_random": null}, "n_envs": 1, "n_steps": 2048, "gamma": 0.98, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}", "__doc__": "\n Rollout buffer used in on-policy algorithms like A2C/PPO.\n It corresponds to ``buffer_size`` transitions collected\n using the current policy.\n This experience will be discarded after the policy update.\n In order to use PPO objective, we also store the current value of each state\n and the log probability of each taken action.\n\n The term rollout here refers to the model-free notion and should not\n be used with the concept of rollout used in model-based RL or planning.\n Hence, it is only involved in policy and value function training but not action selection.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n Equivalent to classic advantage when set to 1.\n :param gamma: Discount factor\n :param n_envs: Number of parallel environments\n ", "__init__": "<function RolloutBuffer.__init__ at 0x79ae83572050>", "reset": "<function RolloutBuffer.reset at 0x79ae835720e0>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x79ae83572170>", "add": "<function RolloutBuffer.add at 0x79ae83572200>", "get": "<function RolloutBuffer.get at 0x79ae83572290>", "_get_samples": "<function RolloutBuffer._get_samples at 0x79ae83572320>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x79ae8355efc0>"}, "rollout_buffer_kwargs": {}, "batch_size": 64, "n_epochs": 10, "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 Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.4.0a7", "PyTorch": "2.3.1+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.26.2"}}
|
|
|
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 0x795124afc0d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x795124afc160>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x795124afc1f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x795124afc280>", "_build": "<function ActorCriticPolicy._build at 0x795124afc310>", "forward": "<function ActorCriticPolicy.forward at 0x795124afc3a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x795124afc430>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x795124afc4c0>", "_predict": "<function ActorCriticPolicy._predict at 0x795124afc550>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x795124afc5e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x795124afc670>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x795124afc700>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x795124aa4f40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 200704, "_total_timesteps": 200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1723454149510199712, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYMAAAAAAAAABRNcD+oibC+KFR8vpSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsDhpSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0035199999999999676, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwIQWyULUkOaMAWyUS8iMAXSUR0B2jKA+Y+jedX2UKGgGR8CHa5zQu27WaAdLyGgIR0B2kDiOvMbFdX2UKGgGR8CMgA9lEqlQaAdLyGgIR0B2k9flZHNHdX2UKGgGR8CVr9aGpMpPaAdLyGgIR0B2l2x1PnB+dX2UKGgGR8CU+fWUKRdQaAdLyGgIR0B2mytLcsUZdX2UKGgGR8CIQ2HGjsUqaAdLyGgIR0B2nrhGYrrgdX2UKGgGR8CUcb3QUpNLaAdLyGgIR0B2olFH8TBZdX2UKGgGR8CHnmjVx0dSaAdLyGgIR0B2phCF9KEndX2UKGgGR8CDpra9sabXaAdLyGgIR0B2v6Ll3hXKdX2UKGgGR8CIWb4wAU+LaAdLyGgIR0B2w0CwKSgXdX2UKGgGR8CM0XQkX1rZaAdLyGgIR0B2xsF0PpY+dX2UKGgGR8CNGBgrpaA4aAdLyGgIR0B2ylGd7OVxdX2UKGgGR8CEZKEVWS2ZaAdLyGgIR0B2zg+u/1xsdX2UKGgGR8CJDbviLl3haAdLyGgIR0B20a7iADq4dX2UKGgGR8CH69xxT850aAdLyGgIR0B21UBS1maqdX2UKGgGR8B/RPh86V+raAdLyGgIR0B22M0BOpKjdX2UKGgGR8CIBQouwosqaAdLyGgIR0B23GZuyeI3dX2UKGgGR8CIBKwUxmCiaAdLyGgIR0B23+0E5hjOdX2UKGgGR8CNMvSZ0CA+aAdLyGgIR0B2+aLP2PDHdX2UKGgGR8CEV+rcTJyRaAdLyGgIR0B2/Vga3qiXdX2UKGgGR8CIPNDcdo38aAdLyGgIR0B3AOvV3EAHdX2UKGgGR8CNQEwQDmr9aAdLyGgIR0B3BHmr8zhxdX2UKGgGR8CQSvjvd/KAaAdLyGgIR0B3CAd7v5P/dX2UKGgGR8CRCDSDh99daAdLyGgIR0B3C4xcmjTKdX2UKGgGR8CD9lux8lXzaAdLyGgIR0B3Dy9CeEqUdX2UKGgGR8CKnUUmD15CaAdLyGgIR0B3ErI3irDJdX2UKGgGR8CIbPbmEGqxaAdLyGgIR0B3Fi8tf5UMdX2UKGgGR8CCoU1UEPlNaAdLyGgIR0B3GbQa72+PdX2UKGgGR8CAEyIwdsBRaAdLyGgIR0B3OrJ2dNFjdX2UKGgGR8CNg+QlruYyaAdLyGgIR0B3QAPd2xIKdX2UKGgGR8CIZkSZBsyjaAdLyGgIR0B3RQpsoDxLdX2UKGgGR8B5BARL9MsZaAdLyGgIR0B3Sm5LAYYSdX2UKGgGR8CRbEnRLK3eaAdLyGgIR0B3Tmkxh2GJdX2UKGgGR8CNUbHbRF7VaAdLyGgIR0B3UiDdxhlUdX2UKGgGR8CKKbZYgaFVaAdLyGgIR0B3VZRl6JIldX2UKGgGR8CQivwkgOjJaAdLyGgIR0B3WQZ/CqIadX2UKGgGR8CHZyEmplz2aAdLyGgIR0B3XJjoZAIIdX2UKGgGR8CH/0ESM98raAdLyGgIR0B3YBiDujREdX2UKGgGR8CCSSPtlZoxaAdLyGgIR0B3Y9IiC8ODdX2UKGgGR8CIBLs3Q2MsaAdLyGgIR0B3fP/5tWMkdX2UKGgGR8CIPIOyVv/BaAdLyGgIR0B3gIvGp++edX2UKGgGR8CHoxyxRl6JaAdLyGgIR0B3hDt7a7EpdX2UKGgGR8CQi9pz90ihaAdLyGgIR0B3iDbItDlYdX2UKGgGR8CMZyl3Qla9aAdLyGgIR0B3i9j6N2kjdX2UKGgGR8CNTNSLqD9PaAdLyGgIR0B3j3CpFTegdX2UKGgGR8CIOxYV6/qPaAdLyGgIR0B3kzSE12q2dX2UKGgGR8CMXZDtw71aaAdLyGgIR0B3lrGkvboKdX2UKGgGR8CH6JWCEpRXaAdLyGgIR0B3mkjyFwkxdX2UKGgGR8CN0RjwQUYbaAdLyGgIR0B3ndalk6LgdX2UKGgGR8B//BQk5ZKWaAdLyGgIR0B3t0yad+XrdX2UKGgGR8B4dpKRMewLaAdLyGgIR0B3ut1HOKO1dX2UKGgGR8CErumMwUQDaAdLyGgIR0B3vn6UJOWTdX2UKGgGR8CLym9Pk7wKaAdLyGgIR0B3wi8pTdcjdX2UKGgGR8B4kZy8zyjIaAdLyGgIR0B3xeCDmKZVdX2UKGgGR8CNZSXCTEBKaAdLyGgIR0B3yW4RVZLadX2UKGgGR8CNds2ZRbbDaAdLyGgIR0B3zQzvZyuIdX2UKGgGR8CEecUD+zdDaAdLyGgIR0B30KtMfzSUdX2UKGgGR8CNOMHgxagVaAdLyGgIR0B31HIT4+KTdX2UKGgGR8CAOtLteD3/aAdLyGgIR0B32AW56MR6dX2UKGgGR8CDYcPatcOcaAdLyGgIR0B38+9US7GvdX2UKGgGR8CGbmdFvybyaAdLyGgIR0B3+HeXRgJDdX2UKGgGR8CEDECtA9mpaAdLyGgIR0B3/PQQcxTLdX2UKGgGR8CEVVlS0jTsaAdLyGgIR0B4Ab15B1LbdX2UKGgGR8CEA/olD4QCaAdLyGgIR0B4BwPI4lyBdX2UKGgGR8CAQyC2+fyxaAdLyGgIR0B4DBhmXgLrdX2UKGgGR8CEZA91U2k0aAdLyGgIR0B4ESYZ2pyZdX2UKGgGR8CEBLM23rleaAdLyGgIR0B4Fpq8DjiodX2UKGgGR8B4cibBoEjgaAdLyGgIR0B4Go2tMfzSdX2UKGgGR8CAIzS/j81oaAdLyGgIR0B4HghQm/nGdX2UKGgGR8CFH0dNnGsFaAdLyGgIR0B4N0Oz6ab4dX2UKGgGR8CKYuclPacqaAdLyGgIR0B4Os6o2n89dX2UKGgGR8CAGY4DLbHqaAdLyGgIR0B4Pl6KLsKLdX2UKGgGR8B+qoFLWZqmaAdLyGgIR0B4Qf9Nvfj0dX2UKGgGR8CEeDW2gFotaAdLyGgIR0B4RYlAu7HydX2UKGgGR8B4aByU9pyqaAdLyGgIR0B4STZRKpT/dX2UKGgGR8CAGwFcpsoEaAdLyGgIR0B4TMjX4CZGdX2UKGgGR8CQQmESM98raAdLyGgIR0B4UE6aLGaQdX2UKGgGR8CIiHpblijMaAdLyGgIR0B4U89eQdS3dX2UKGgGR8CBRLXoTwlTaAdLyGgIR0B4V2yTpxFRdX2UKGgGR8CEAsh/y5I6aAdLyGgIR0B4WxYHPeHjdX2UKGgGR8CKgugQHzH0aAdLyGgIR0B4dBQP7N0OdX2UKGgGR8CPS1fHggoxaAdLyGgIR0B4d5SzgMtsdX2UKGgGR8B4rQNZvDP4aAdLyGgIR0B4e1ruYx+KdX2UKGgGR8CAC1NKyv9taAdLyGgIR0B4fw1NxlxwdX2UKGgGR8B8iHBbfP5YaAdLyGgIR0B4gqOAAhjfdX2UKGgGR8CAbDZg5R0maAdLyGgIR0B4hiWjXWe6dX2UKGgGR8CERXdUKiPAaAdLyGgIR0B4idL8JlasdX2UKGgGR8CILyUcGTs6aAdLyGgIR0B4jXLt/nW8dX2UKGgGR8CAjo4ZMtbtaAdLyGgIR0B4kQfPomojdX2UKGgGR8CEkwyjYZl4aAdLyGgIR0B4lNWYF7ladX2UKGgGR8CAQmlTm4iHaAdLyGgIR0B4rmLDQ7cPdX2UKGgGR8CEYUqEOAiFaAdLyGgIR0B4sfhqCYkWdX2UKGgGR8CJlAkJrtVraAdLyGgIR0B4tX3yqdYodX2UKGgGR8ByHwUIsyzpaAdLyGgIR0B4udMPBi1BdX2UKGgGR8B4NgaisXBQaAdLyGgIR0B4vsTEit7sdX2UKGgGR8CIlgM2FWXDaAdLyGgIR0B4w2zyBkI5dX2UKGgGR8CAFaO+7Dl6aAdLyGgIR0B4x+NR3u/ldX2UKGgGR8CAGHW+49X+aAdLyGgIR0B4zLjKgZjydX2UKGgGR8B4m5UNrj5saAdLyGgIR0B40cDEFW4mdX2UKGgGR8B4Vxc2R7qqaAdLyGgIR0B41satLcsUdWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 980, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True]", "bounded_above": "[ True True True]", "_shape": [3], "low": "[-1. -1. -8.]", "high": "[1. 1. 8.]", "low_repr": "[-1. -1. -8.]", "high_repr": "[1. 1. 8.]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True]", "bounded_above": "[ True]", "_shape": [1], "low": "[-2.]", "high": "[2.]", "low_repr": "-2.0", "high_repr": "2.0", "_np_random": null}, "n_envs": 1, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "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 Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.1+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
ppo-Pendulum-v1.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92eaf9c49b764445bcbcbf9991cf46490b0b6ea2265f65344bfeb4c04b21f4fb
|
3 |
+
size 138038
|
ppo-Pendulum-v1/_stable_baselines3_version
CHANGED
@@ -1 +1 @@
|
|
1 |
-
2.
|
|
|
1 |
+
2.0.0a5
|
ppo-Pendulum-v1/data
CHANGED
@@ -4,34 +4,34 @@
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__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 ",
|
7 |
-
"__init__": "<function ActorCriticPolicy.__init__ at
|
8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
11 |
-
"_build": "<function ActorCriticPolicy._build at
|
12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
13 |
-
"extract_features": "<function ActorCriticPolicy.extract_features at
|
14 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
15 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
16 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
17 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
18 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
-
"_abc_impl": "<_abc._abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
-
"num_timesteps":
|
25 |
-
"_total_timesteps":
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
-
"start_time":
|
30 |
-
"learning_rate": 0.
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
-
":serialized:": "
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -39,19 +39,19 @@
|
|
39 |
},
|
40 |
"_last_original_obs": null,
|
41 |
"_episode_num": 0,
|
42 |
-
"use_sde":
|
43 |
-
"sde_sample_freq":
|
44 |
"_current_progress_remaining": -0.0035199999999999676,
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
-
":serialized:": "
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
-
"_n_updates":
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "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",
|
@@ -84,38 +84,22 @@
|
|
84 |
},
|
85 |
"n_envs": 1,
|
86 |
"n_steps": 2048,
|
87 |
-
"gamma": 0.
|
88 |
"gae_lambda": 0.95,
|
89 |
"ent_coef": 0.0,
|
90 |
"vf_coef": 0.5,
|
91 |
"max_grad_norm": 0.5,
|
92 |
-
"rollout_buffer_class": {
|
93 |
-
":type:": "<class 'abc.ABCMeta'>",
|
94 |
-
":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=",
|
95 |
-
"__module__": "stable_baselines3.common.buffers",
|
96 |
-
"__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}",
|
97 |
-
"__doc__": "\n Rollout buffer used in on-policy algorithms like A2C/PPO.\n It corresponds to ``buffer_size`` transitions collected\n using the current policy.\n This experience will be discarded after the policy update.\n In order to use PPO objective, we also store the current value of each state\n and the log probability of each taken action.\n\n The term rollout here refers to the model-free notion and should not\n be used with the concept of rollout used in model-based RL or planning.\n Hence, it is only involved in policy and value function training but not action selection.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n Equivalent to classic advantage when set to 1.\n :param gamma: Discount factor\n :param n_envs: Number of parallel environments\n ",
|
98 |
-
"__init__": "<function RolloutBuffer.__init__ at 0x79ae83572050>",
|
99 |
-
"reset": "<function RolloutBuffer.reset at 0x79ae835720e0>",
|
100 |
-
"compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x79ae83572170>",
|
101 |
-
"add": "<function RolloutBuffer.add at 0x79ae83572200>",
|
102 |
-
"get": "<function RolloutBuffer.get at 0x79ae83572290>",
|
103 |
-
"_get_samples": "<function RolloutBuffer._get_samples at 0x79ae83572320>",
|
104 |
-
"__abstractmethods__": "frozenset()",
|
105 |
-
"_abc_impl": "<_abc._abc_data object at 0x79ae8355efc0>"
|
106 |
-
},
|
107 |
-
"rollout_buffer_kwargs": {},
|
108 |
"batch_size": 64,
|
109 |
"n_epochs": 10,
|
110 |
"clip_range": {
|
111 |
":type:": "<class 'function'>",
|
112 |
-
":serialized:": "
|
113 |
},
|
114 |
"clip_range_vf": null,
|
115 |
"normalize_advantage": true,
|
116 |
"target_kl": null,
|
117 |
"lr_schedule": {
|
118 |
":type:": "<class 'function'>",
|
119 |
-
":serialized:": "
|
120 |
}
|
121 |
}
|
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__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 ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x795124afc0d0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x795124afc160>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x795124afc1f0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x795124afc280>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x795124afc310>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x795124afc3a0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x795124afc430>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x795124afc4c0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x795124afc550>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x795124afc5e0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x795124afc670>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x795124afc700>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x795124aa4f40>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 200704,
|
25 |
+
"_total_timesteps": 200000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1723454149510199712,
|
30 |
+
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "gAWVgQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYMAAAAAAAAABRNcD+oibC+KFR8vpSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsDhpSMAUOUdJRSlC4="
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
39 |
},
|
40 |
"_last_original_obs": null,
|
41 |
"_episode_num": 0,
|
42 |
+
"use_sde": false,
|
43 |
+
"sde_sample_freq": -1,
|
44 |
"_current_progress_remaining": -0.0035199999999999676,
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "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"
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
+
"_n_updates": 980,
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "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",
|
|
|
84 |
},
|
85 |
"n_envs": 1,
|
86 |
"n_steps": 2048,
|
87 |
+
"gamma": 0.99,
|
88 |
"gae_lambda": 0.95,
|
89 |
"ent_coef": 0.0,
|
90 |
"vf_coef": 0.5,
|
91 |
"max_grad_norm": 0.5,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
92 |
"batch_size": 64,
|
93 |
"n_epochs": 10,
|
94 |
"clip_range": {
|
95 |
":type:": "<class 'function'>",
|
96 |
+
":serialized:": "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"
|
97 |
},
|
98 |
"clip_range_vf": null,
|
99 |
"normalize_advantage": true,
|
100 |
"target_kl": null,
|
101 |
"lr_schedule": {
|
102 |
":type:": "<class 'function'>",
|
103 |
+
":serialized:": "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"
|
104 |
}
|
105 |
}
|
ppo-Pendulum-v1/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:262c7010c9091544d6e3aed7daafd65d4f792a877609e48ba0c7a8967a0d6e90
|
3 |
+
size 82401
|
ppo-Pendulum-v1/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ecdec6b1623b7fc0a35a50f727fab64fda51c27c0e50d861ddb7b5b04373a4c
|
3 |
+
size 40751
|
ppo-Pendulum-v1/system_info.txt
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
|
2 |
- Python: 3.10.12
|
3 |
-
- Stable-Baselines3: 2.
|
4 |
- PyTorch: 2.3.1+cu121
|
5 |
- GPU Enabled: True
|
6 |
- Numpy: 1.26.4
|
7 |
- Cloudpickle: 2.2.1
|
8 |
-
- Gymnasium: 0.
|
9 |
-
- OpenAI Gym: 0.
|
|
|
1 |
- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
|
2 |
- Python: 3.10.12
|
3 |
+
- Stable-Baselines3: 2.0.0a5
|
4 |
- PyTorch: 2.3.1+cu121
|
5 |
- GPU Enabled: True
|
6 |
- Numpy: 1.26.4
|
7 |
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.25.2
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward": -
|
|
|
1 |
+
{"mean_reward": -421.51727310000007, "std_reward": 342.0916223275373, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-12T09:22:46.954266"}
|