tensortrade.agents.parallel.parallel_dqn_trainer module

class tensortrade.agents.parallel.parallel_dqn_trainer.ParallelDQNTrainer(agent: ParallelDQNAgent, create_env: Callable[[None], TrainingEnvironment], memory_queue: multiprocessing.context.BaseContext.Queue, model_update_queue: multiprocessing.context.BaseContext.Queue, done_queue: multiprocessing.context.BaseContext.Queue, n_steps: int, n_episodes: int, eps_end: int = 0.05, eps_start: int = 0.99, eps_decay_steps: int = 2000, update_target_every: int = 2)[source]

Bases: multiprocessing.context.Process

run()[source]

Method to be run in sub-process; can be overridden in sub-class