tensortrade.agents.dqn_agent module

class tensortrade.agents.dqn_agent.DQNAgent(env: TradingEnv, policy_network: <sphinx.ext.autodoc.importer._MockObject object at 0x7f37561e1b90> = None)

Bases: tensortrade.agents.agent.Agent

• https://towardsdatascience.com/deep-reinforcement-learning-build-a-deep-q-network-dqn-to-play-cartpole-with-tensorflow-2-and-gym-8e105744b998
• https://pytorch.org/tutorials/intermediate/reinforcement_q_learning.html#dqn-algorithm
• https://arxiv.org/abs/1802.00308

get_action(state: numpy.ndarray, **kwargs) → int

Get an action for a specific state in the environment.

restore(path: str, **kwargs)

Restore the agent from the file specified in path.

save(path: str, **kwargs)

Save the agent to the directory specified in path.

train(n_steps: int = 1000, n_episodes: int = 10, save_every: int = None, save_path: str = 'agent/', callback: callable = None, **kwargs) → float

Train the agent in the environment and return the mean reward.

class tensortrade.agents.dqn_agent.DQNTransition(state, action, reward, next_state, done)

Bases: tuple

action

Alias for field number 1

done

Alias for field number 4

next_state

Alias for field number 3

reward

Alias for field number 2

state

Alias for field number 0