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 2103.06473cs.LGcs.AI
收藏

有敌手的多任务联合强化学习

Multi-Task Federated Reinforcement Learning with Adversaries

Georgia Institute of Technology(佐治亚理工学院)

Aqeel Anwar, Arijit Raychowdhury

摘要:

强化学习算法,就像任何其他机器学习算法一样,对对手构成严重威胁。对手可以操纵学习算法,导致非最优策略。在本文中,我们分析了多任务联合强化学习算法,其中多个合作代理在各种环境中试图最大化折扣收益之和,在对抗代理的存在下。针对常见的攻击方法不能保证对多任务联合强化学习进行成功攻击的问题,提出了一种具有更好攻击性能的自适应攻击方法。此外,我们修改了传统的联邦强化学习算法,以解决对手的问题,同样适用于没有对手。对不同的中小型强化学习问题的实验表明,该攻击方法优于其他一般攻击方法,并且在对抗代理存在的情况下,对联邦强化学习算法的改进能够实现接近最优的策略。

英文摘要:

Reinforcement learning algorithms, just like any other Machine learning algorithm pose a serious threat from adversaries. The adversaries can manipulate the learning algorithm resulting in non-optimal policies. In this paper, we analyze the Multi-task Federated Reinforcement Learning algorithms, where multiple collaborative agents in various environments are trying to maximize the sum of discounted return, in the presence of adversarial agents. We argue that the common attack methods are not guaranteed to carry out a successful attack on Multi-task Federated Reinforcement Learning and propose an adaptive attack method with better attack performance. Furthermore, we modify the conventional federated reinforcement learning algorithm to address the issue of adversaries that works equally well with and without the adversaries. Experimentation on different small to mid-size reinforcement learning problems show that the proposed attack method outperforms other general attack methods and the proposed modification to federated reinforcement learning algorithm was able to achieve near-optimal policies in the presence of adversarial agents.

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。

↑