Method __init__

examples/DeepQNetwork/expreplay.py:278–317

Args: predictor_io_names (tuple of list of str): input/output names to predict Q value from state. get_player (-> gym.Env): a callable which returns a player. num_parallel_players (int): number of players to run in parallel.

(self,
                 predictor_io_names,
                 get_player,
                 num_parallel_players,
                 state_shape,
                 batch_size,
                 memory_size, init_memory_size,
                 update_frequency, history_len,
                 state_dtype='uint8')

    """

    def __init__(self,
                 predictor_io_names,
                 get_player,
                 num_parallel_players,
                 state_shape,
                 batch_size,
                 memory_size, init_memory_size,
                 update_frequency, history_len,
                 state_dtype='uint8'):
        """
        Args:
            predictor_io_names (tuple of list of str): input/output names to
                predict Q value from state.
            get_player (-> gym.Env): a callable which returns a player.
            num_parallel_players (int): number of players to run in parallel.
                Standard DQN uses 1.
                Parallelism increases speed, but will affect the distribution of
                experiences in the replay buffer.
            state_shape (tuple):
            batch_size (int):
            memory_size (int):
            init_memory_size (int):
            update_frequency (int): number of new transitions to add to memory
                after sampling a batch of transitions for training.
            history_len (int): length of history frames to concat. Zero-filled
                initial frames.
            state_dtype (str):
        """
        assert len(state_shape) in [1, 2, 3], state_shape
        init_memory_size = int(init_memory_size)

        for k, v in locals().items():
            if k != 'self':
                setattr(self, k, v)
        self.exploration = 1.0  # default initial exploration

        self.rng = get_rng(self)
        self._init_memory_flag = threading.Event()  # tell if memory has been initialized

        self.mem = ReplayMemory(memory_size, state_shape, self.history_len, dtype=state_dtype)

    def _init_memory(self):
        logger.info("Populating replay memory with epsilon={} ...".format(self.exploration))