tensortrade.agents.parallel.parallel_dqn_model module¶

class tensortrade.agents.parallel.parallel_dqn_model.ParallelDQNModel(create_env: Callable[TradingEnvironment], policy_network: tensorflow.keras.Model = None)[source]¶

Bases: object

get_action(state: numpy.ndarray, **kwargs) → int [source]¶

restore(path: str, **kwargs)[source]¶

save(path: str, **kwargs)[source]¶

update_networks(model: tensortrade.agents.parallel.parallel_dqn_model.ParallelDQNModel)[source]¶

update_target_network()[source]¶