| { | |
| "policy_class": { | |
| ":type:": "<class 'abc.ABCMeta'>", | |
| ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=", | |
| "__module__": "stable_baselines3.common.policies", | |
| "__doc__": "\n MultiInputActorClass 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 (Tuple)\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: Uses the CombinedExtractor\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 MultiInputActorCriticPolicy.__init__ at 0x7fb824605ea0>", | |
| "__abstractmethods__": "frozenset()", | |
| "_abc_impl": "<_abc._abc_data object at 0x7fb824620580>" | |
| }, | |
| "verbose": 1, | |
| "policy_kwargs": { | |
| ":type:": "<class 'dict'>", | |
| ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", | |
| "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", | |
| "optimizer_kwargs": { | |
| "alpha": 0.99, | |
| "eps": 1e-05, | |
| "weight_decay": 0 | |
| } | |
| }, | |
| "num_timesteps": 0, | |
| "_total_timesteps": 1000000, | |
| "_num_timesteps_at_start": 0, | |
| "seed": null, | |
| "action_noise": null, | |
| "start_time": 1682692656001741340, | |
| "learning_rate": 0.0007, | |
| "tensorboard_log": null, | |
| "lr_schedule": { | |
| ":type:": "<class 'function'>", | |
| ":serialized:": "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" | |
| }, | |
| "_last_obs": { | |
| ":type:": "<class 'collections.OrderedDict'>", | |
| ":serialized:": "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", | |
| "achieved_goal": "[[0.4539383 0.02294795 0.68542385]\n [0.4539383 0.02294795 0.68542385]\n [0.4539383 0.02294795 0.68542385]\n [0.4539383 0.02294795 0.68542385]]", | |
| "desired_goal": "[[-0.611809 0.04745473 -0.06364378]\n [-1.3843648 -1.622876 -1.5261958 ]\n [ 0.60735244 -0.03059616 -1.3670847 ]\n [-0.93167 0.30337122 0.06303658]]", | |
| "observation": "[[0.4539383 0.02294795 0.68542385 0.01889677 0.00311491 0.0302433 ]\n [0.4539383 0.02294795 0.68542385 0.01889677 0.00311491 0.0302433 ]\n [0.4539383 0.02294795 0.68542385 0.01889677 0.00311491 0.0302433 ]\n [0.4539383 0.02294795 0.68542385 0.01889677 0.00311491 0.0302433 ]]" | |
| }, | |
| "_last_episode_starts": { | |
| ":type:": "<class 'numpy.ndarray'>", | |
| ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg==" | |
| }, | |
| "_last_original_obs": { | |
| ":type:": "<class 'collections.OrderedDict'>", | |
| ":serialized:": "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", | |
| "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]]", | |
| "desired_goal": "[[-0.12196851 0.12455483 0.13102914]\n [-0.14289069 0.08489503 0.2588914 ]\n [ 0.11630604 0.03255973 0.25564012]\n [ 0.05255869 -0.11457129 0.26169795]]", | |
| "observation": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]]" | |
| }, | |
| "_episode_num": 0, | |
| "use_sde": false, | |
| "sde_sample_freq": -1, | |
| "_current_progress_remaining": 0.0, | |
| "_stats_window_size": 100, | |
| "ep_info_buffer": { | |
| ":type:": "<class 'collections.deque'>", | |
| ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg==" | |
| }, | |
| "ep_success_buffer": { | |
| ":type:": "<class 'collections.deque'>", | |
| ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg==" | |
| }, | |
| "_n_updates": 50000, | |
| "n_steps": 5, | |
| "gamma": 0.99, | |
| "gae_lambda": 1.0, | |
| "ent_coef": 0.0, | |
| "vf_coef": 0.5, | |
| "max_grad_norm": 0.5, | |
| "normalize_advantage": false, | |
| "observation_space": { | |
| ":type:": "<class 'gym.spaces.dict.Dict'>", | |
| ":serialized:": "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", | |
| "spaces": "OrderedDict([('achieved_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('desired_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('observation', Box([-10. -10. -10. -10. -10. -10.], [10. 10. 10. 10. 10. 10.], (6,), float32))])", | |
| "_shape": null, | |
| "dtype": null, | |
| "_np_random": null | |
| }, | |
| "action_space": { | |
| ":type:": "<class 'gym.spaces.box.Box'>", | |
| ":serialized:": "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", | |
| "dtype": "float32", | |
| "_shape": [ | |
| 3 | |
| ], | |
| "low": "[-1. -1. -1.]", | |
| "high": "[1. 1. 1.]", | |
| "bounded_below": "[ True True True]", | |
| "bounded_above": "[ True True True]", | |
| "_np_random": null | |
| }, | |
| "n_envs": 4 | |
| } |