tensortrade.agents.a2c_agent module¶

References

class tensortrade.agents.a2c_agent.A2CAgent(env, shared_network=None, actor_network=None, critic_network=None)[source]¶

get_action(state, **kwargs)[source]¶

Get an action for a specific state in the environment.

Return type:	`int`

restore(path, **kwargs)[source]¶: Restore the agent from the file specified in path.

save(path, **kwargs)[source]¶: Save the agent to the directory specified in path.

train(n_steps=None, n_episodes=None, save_every=None, save_path=None, callback=None, **kwargs)[source]¶

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

Return type:	`float`

class tensortrade.agents.a2c_agent.A2CTransition(state, action, reward, done, value)¶