7384719699a07a5298c29f3205859b45533853ae,chainerrl/agents/dqn.py,DQN,act,#DQN#Any#,304

Before Change

        qout = self.model(self.batch_states([state], self.xp, self.phi),
                          test=True)
        action = cuda.to_cpu(qout.greedy_actions.data)[0]
        action_var = chainer.Variable(self.xp.asarray([action]))
        q = float(qout.evaluate_actions(action_var).data)

        // Update stats
        self.average_q *= self.average_q_decay
        self.average_q += (1 - self.average_q_decay) * q

After Change

            model.to_cpu()

    def act(self, state):
        with chainer.no_backprop_mode():
            action_value = self.model(
                self.batch_states([state], self.xp, self.phi), test=True)
            q = float(action_value.max.data)
            action = cuda.to_cpu(action_value.greedy_actions.data)[0]

        // Update stats
        self.average_q *= self.average_q_decay
        self.average_q += (1 - self.average_q_decay) * q

        self.logger.debug("t:%s q:%s action_value:%s", self.t, q, action_value)

Instances