dqn_agent.hpp File Reference

Epsilon-greedy DQN policy over an arbitrary Q-network Module. More...

#include <cstdint>
#include "pulsatrix/agent.hpp"
#include "pulsatrix/device_backend.hpp"
#include "pulsatrix/module.hpp"
#include "pulsatrix/tensor.hpp"

Include dependency graph for dqn_agent.hpp:

Go to the source code of this file.

Classes
class	pulsatrix::DQNAgent
	The epsilon-greedy behaviour policy of Mnih et al. 2015: with probability epsilon act uniformly at random, otherwise take argmax_a Q(observation, a). More...

Namespaces
namespace	pulsatrix

Detailed Description

Epsilon-greedy DQN policy over an arbitrary Q-network Module.