PPO-LunarLander-v2 / config.json
JaiSurya's picture
Updating the PPO agent
3ec724c
{"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 0x79b9787f1090>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79b9787f1120>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79b9787f11b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79b9787f1240>", "_build": "<function ActorCriticPolicy._build at 0x79b9787f12d0>", "forward": "<function ActorCriticPolicy.forward at 0x79b9787f1360>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x79b9787f13f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79b9787f1480>", "_predict": "<function ActorCriticPolicy._predict at 0x79b9787f1510>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79b9787f15a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79b9787f1630>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x79b9787f16c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x79b9787f46c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2500608, "_total_timesteps": 2500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1700830269684855999, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAADNhcb171pO68iCGtVZAALGEmDg7jCO4NAAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_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": -0.00024320000000011, "_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": 12210, "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 1024, "gamma": 0.995, "gae_lambda": 0.98, "ent_coef": 0.0001, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 5, "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-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}