dqn.py 文件源码

def _compute_y_and_t(self, exp_batch, gamma):
        batch_size = exp_batch['reward'].shape[0]

        # Compute Q-values for current states
        batch_state = exp_batch['state']

        qout = self.model(batch_state)

        batch_actions = exp_batch['action']
        batch_q = F.reshape(qout.evaluate_actions(
            batch_actions), (batch_size, 1))

        with chainer.no_backprop_mode():
            batch_q_target = F.reshape(
                self._compute_target_values(exp_batch, gamma),
                (batch_size, 1))

        return batch_q, batch_q_target