9801f28774b8d4aeed7d65025bf2451814c1db6d,chainerrl/agents/ddpg.py,DDPG,batch_act,#DDPG#Any#,347

Before Change

            batch_xs = self.batch_states(
                [[obs] for obs in batch_obs],
                self.xp, self.phi)
            batch_action = [
                self.policy(batch_xs[i]).sample()
                for i in range(len(batch_obs))]
            // Q is not needed here, but log it just for information
            // q = self.q_function(batch_xs, batch_action)

        // Update stats

After Change

        with chainer.using_config("train", False), chainer.no_backprop_mode():
            batch_xs = self.batch_states(batch_obs,
                self.xp, self.phi)
            batch_action = self.policy(batch_xs).sample()
            // Q is not needed here, but log it just for information
            q = self.q_function(batch_xs, batch_action)

        // Update stats

Instances