ppo-FrozenLake-v1 / config.json
mindwrapped's picture
Upload PPO FrozenLake-v1 trained agent
6602069
{"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 0x7fca3ab08dd0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fca3ab08e60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fca3ab08ef0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fca3ab08f80>", "_build": "<function ActorCriticPolicy._build at 0x7fca3aa8e050>", "forward": "<function ActorCriticPolicy.forward at 0x7fca3aa8e0e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fca3aa8e170>", "_predict": "<function ActorCriticPolicy._predict at 0x7fca3aa8e200>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fca3aa8e290>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fca3aa8e320>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fca3aa8e3b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fca3aade390>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLEIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 16, "_shape": [], "dtype": "int64", "_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": 700000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1653007487.134639, "learning_rate": 0.0003, "tensorboard_log": "runs/20xd30z1", "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV8wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAAQAAAAAAAAABgAAAAAAAAAJAAAAAAAAAAAAAAAAAAAACAAAAAAAAAAEAAAAAAAAAAgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAgAAAAAAAAACQAAAAAAAAAEAAAAAAAAAAkAAAAAAAAACQAAAAAAAAAJAAAAAAAAAAgAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_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": 0.31187200000000004, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 168, "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:": "gAWVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}