arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2003.10181cs.LGstat.ML
收藏

在Atari的深度强化学习中使用适当基线评估数据效率的重要性

Importance of using appropriate baselines for evaluation of data-efficiency in deep reinforcement learning for Atari

University of Birmingham(伯明翰大学)

Kacper Kielak

摘要:

强化学习(RL)在过去几年中取得了巨大的进步。尽管如此,RL社区的共识是,目前使用的方法,尽管它们有很多好处,但数据效率极低,特别是在Atari这样的丰富视觉领域。为了避免这个问题,引入了新的方法,这些方法通常声称比最先进的DQN算法的流行变体更有效。然而,在本文中,我们证明了新提出的技术只是在实验中使用了不公平的基线。也就是说,我们证明了效率的实际提高来自于允许算法对每个数据样本进行更多的训练更新,而不是采用新方法。通过允许DQN更频繁地执行网络更新,我们设法达到了与最近提出的改进类似或更好的结果,而复杂性和计算成本通常只是一小部分。此外,根据研究结果,我们认为,类似于本文中提出的修改后的DQN的代理应该被用作未来任何旨在提高深度强化学习样本效率的工作的基线。

英文摘要:

Reinforcement learning (RL) has seen great advancements in the past few years. Nevertheless, the consensus among the RL community is that currently used methods, despite all their benefits, suffer from extreme data inefficiency, especially in the rich visual domains like Atari. To circumvent this problem, novel approaches were introduced that often claim to be much more efficient than popular variations of the state-of-the-art DQN algorithm. In this paper, however, we demonstrate that the newly proposed techniques simply used unfair baselines in their experiments. Namely, we show that the actual improvement in the efficiency came from allowing the algorithm for more training updates for each data sample, and not from employing the new methods. By allowing DQN to execute network updates more frequently we manage to reach similar or better results than the recently proposed advancement, often at a fraction of complexity and computational costs. Furthermore, based on the outcomes of the study, we argue that the agent similar to the modified DQN that is presented in this paper should be used as a baseline for any future work aimed at improving sample efficiency of deep reinforcement learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑