ppo-Acrobot-v1 / config.json
Sosties's picture
Upload PPO Acrobot-v1 trained agent
169b255 verified
raw
history blame
13.3 kB
{"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 0x7b4ba0b30280>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b4ba0b30310>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b4ba0b303a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b4ba0b30430>", "_build": "<function ActorCriticPolicy._build at 0x7b4ba0b304c0>", "forward": "<function ActorCriticPolicy.forward at 0x7b4ba0b30550>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b4ba0b305e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b4ba0b30670>", "_predict": "<function ActorCriticPolicy._predict at 0x7b4ba0b30700>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b4ba0b30790>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b4ba0b30820>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b4ba0b308b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b4ba1442e40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2009088, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1718769833190393817, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYSAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLEoWUjAFDlHSUUpQu"}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0045440000000001035, "_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": 436, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True]", "bounded_above": "[ True True True True True True]", "_shape": [6], "low": "[ -1. -1. -1. -1. -12.566371 -28.274334]", "high": "[ 1. 1. 1. 1. 12.566371 28.274334]", "low_repr": "[ -1. -1. -1. -1. -12.566371 -28.274334]", "high_repr": "[ 1. 1. 1. 1. 12.566371 28.274334]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAwAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "3", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 18, "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 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"}}