agents/dqn_v2-8/config.json

{
  "policy_class": {
    ":type:": "<class 'abc.ABCMeta'>",
    "__module__": "stable_baselines3.dqn.policies",
    "__doc__": "\n    Policy class for DQN when using images as input.\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 features_extractor_class: Features extractor to use.\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 CnnPolicy.__init__ at 0x7d6123a05cf0>",
    "__abstractmethods__": "frozenset()",
    "_abc_impl": "<_abc._abc_data object at 0x7d6123a18580>"
  },
  "verbose": 1,
  "policy_kwargs": {},
  "num_timesteps": 10000000,
  "_total_timesteps": 10000000,
  "_num_timesteps_at_start": 9000000,
  "seed": null,
  "action_noise": null,
  "start_time": 1715963247524276127,
  "learning_rate": 5e-05,
  "tensorboard_log": "./",
  "_last_obs": {
    ":type:": "<class 'numpy.ndarray'>"
  },
  "_last_episode_starts": {
    ":type:": "<class 'numpy.ndarray'>"
  },
  "_last_original_obs": {
    ":type:": "<class 'numpy.ndarray'>"
  },
  "_episode_num": 8626,
  "use_sde": false,
  "sde_sample_freq": -1,
  "_current_progress_remaining": 0.0,
  "_stats_window_size": 100,
  "ep_info_buffer": {
    ":type:": "<class 'collections.deque'>"
  },
  "ep_success_buffer": {
    ":type:": "<class 'collections.deque'>"
  },
  "_n_updates": 2487500,
  "observation_space": {
    ":type:": "<class 'gymnasium.spaces.box.Box'>",
    "dtype": "uint8",
    "bounded_below": "[[[ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]\n  ...\n  [ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]]\n\n [[ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]\n  ...\n  [ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]]\n\n [[ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]\n  ...\n  [ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]]]",
    "bounded_above": "[[[ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]\n  ...\n  [ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]]\n\n [[ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]\n  ...\n  [ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]]\n\n [[ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]\n  ...\n  [ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]\n  [ True  True  True ...  True  True  True]]]",
    "_shape": [
      3,
      250,
      160
    ],
    "low": "[[[0 0 0 ... 0 0 0]\n  [0 0 0 ... 0 0 0]\n  [0 0 0 ... 0 0 0]\n  ...\n  [0 0 0 ... 0 0 0]\n  [0 0 0 ... 0 0 0]\n  [0 0 0 ... 0 0 0]]\n\n [[0 0 0 ... 0 0 0]\n  [0 0 0 ... 0 0 0]\n  [0 0 0 ... 0 0 0]\n  ...\n  [0 0 0 ... 0 0 0]\n  [0 0 0 ... 0 0 0]\n  [0 0 0 ... 0 0 0]]\n\n [[0 0 0 ... 0 0 0]\n  [0 0 0 ... 0 0 0]\n  [0 0 0 ... 0 0 0]\n  ...\n  [0 0 0 ... 0 0 0]\n  [0 0 0 ... 0 0 0]\n  [0 0 0 ... 0 0 0]]]",
    "high": "[[[255 255 255 ... 255 255 255]\n  [255 255 255 ... 255 255 255]\n  [255 255 255 ... 255 255 255]\n  ...\n  [255 255 255 ... 255 255 255]\n  [255 255 255 ... 255 255 255]\n  [255 255 255 ... 255 255 255]]\n\n [[255 255 255 ... 255 255 255]\n  [255 255 255 ... 255 255 255]\n  [255 255 255 ... 255 255 255]\n  ...\n  [255 255 255 ... 255 255 255]\n  [255 255 255 ... 255 255 255]\n  [255 255 255 ... 255 255 255]]\n\n [[255 255 255 ... 255 255 255]\n  [255 255 255 ... 255 255 255]\n  [255 255 255 ... 255 255 255]\n  ...\n  [255 255 255 ... 255 255 255]\n  [255 255 255 ... 255 255 255]\n  [255 255 255 ... 255 255 255]]]",
    "low_repr": "0",
    "high_repr": "255",
    "_np_random": "Generator(PCG64)"
  },
  "action_space": {
    ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
    "n": "5",
    "start": "0",
    "_shape": [],
    "dtype": "int64",
    "_np_random": "Generator(PCG64)"
  },
  "n_envs": 1,
  "buffer_size": 70000,
  "batch_size": 64,
  "learning_starts": 100000,
  "tau": 1.0,
  "gamma": 0.999,
  "gradient_steps": 1,
  "optimize_memory_usage": false,
  "replay_buffer_class": {
    ":type:": "<class 'abc.ABCMeta'>",
    "__module__": "stable_baselines3.common.buffers",
    "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\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 n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n        Cannot be used in combination with handle_timeout_termination.\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ",
    "__init__": "<function ReplayBuffer.__init__ at 0x7d61239e1cf0>",
    "add": "<function ReplayBuffer.add at 0x7d61239e1d80>",
    "sample": "<function ReplayBuffer.sample at 0x7d61239e1e10>",
    "_get_samples": "<function ReplayBuffer._get_samples at 0x7d61239e1ea0>",
    "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7d61239e1f30>)>",
    "__abstractmethods__": "frozenset()",
    "_abc_impl": "<_abc._abc_data object at 0x7d61239e61c0>"
  },
  "replay_buffer_kwargs": {},
  "train_freq": {
    ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>"
  },
  "use_sde_at_warmup": false,
  "exploration_initial_eps": 1.0,
  "exploration_final_eps": 0.005,
  "exploration_fraction": 0.3,
  "target_update_interval": 1000,
  "_n_calls": 10000000,
  "max_grad_norm": 10,
  "exploration_rate": 0.005,
  "lr_schedule": {
    ":type:": "<class 'function'>"
  },
  "batch_norm_stats": [],
  "batch_norm_stats_target": [],
  "exploration_schedule": {
    ":type:": "<class 'function'>"
  }
}