tensortrade.agents.dqn_agent module

References

• 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

class tensortrade.agents.dqn_agent.DQNAgent(env, policy_network=None)

Bases: tensortrade.agents.agent.Agent

get_action(state, **kwargs)

Return type:int

restore(path, **kwargs)

save(path, **kwargs)

train(n_steps=None, n_episodes=None, save_every=None, save_path=None, callback=None, **kwargs)

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