DQN's masked-MSE Bellman loss – squared error on the taken action only. More...

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

Include dependency graph for dqn_loss.hpp:

Classes
class	pulsatrix::DQNLoss
	loss = mean_b( (q_values[b, a_b] - targets[b,0])^2 ), where `a_b` is the action actually taken on transition `b` – the semi-gradient TD update of Mnih et al. 2015. More...

Detailed Description

DQN's masked-MSE Bellman loss – squared error on the taken action only.

Classes