def eval()

in train.py [0:0]

• 22 lines of code
• 3 McCabe index (conditional complexity)

    def eval(self):
        step, episode, total_reward = 0, 0, 0
        eval_until_episode = utils.Until(self.cfg.num_eval_episodes)

        while eval_until_episode(episode):
            time_step = self.eval_env.reset()
            self.video_recorder.init(self.eval_env, enabled=(episode == 0))
            while not time_step.last():
                with torch.no_grad(), utils.eval_mode(self.agent):
                    action = self.agent.act(time_step.observation,
                                            self.global_step,
                                            eval_mode=True)
                time_step = self.eval_env.step(action)
                self.video_recorder.record(self.eval_env)
                total_reward += time_step.reward
                step += 1

            episode += 1
            self.video_recorder.save(f'{self.global_frame}.mp4')

        with self.logger.log_and_dump_ctx(self.global_frame, ty='eval') as log:
            log('episode_reward', total_reward / episode)
            log('episode_length', step * self.cfg.action_repeat / episode)
            log('episode', self.global_episode)
            log('step', self.global_step)