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 2203.03535cs.LGcs.AIcs.MA
收藏

影响多智能体强化学习中的长期行为

Influencing Long-Term Behavior in Multiagent Reinforcement Learning

MIT(麻省理工学院);MIT-IBM Watson AI Lab(麻省理工学院-IBM沃森人工智能实验室);Mila(米拉人工智能研究所);University of Oxford(牛津大学)

Dong-Ki Kim, Matthew Riemer, Miao Liu, Jakob N. Foerster, Michael Everett, Chuangchuang Sun, Gerald Tesauro, Jonathan P. How

摘要:

多智能体强化学习的主要挑战是在其他同时学习的智能体存在的情况下学习有用的策略的困难,这些智能体的变化行为共同影响环境的过渡和奖励动态。最近出现的一种解决这种非平稳性的有效方法是每个代理预测其他代理的学习,并影响未来政策的演变,以实现自己的利益。不幸的是,以前实现这一目标的方法受到短视评估的影响,只考虑有限数量的政策更新。因此,这些方法只能影响短暂的未来政策,而不是实现可扩展的均衡选择方法,影响收敛时的行为的承诺。在本文中,我们提出了一个原则性的框架,考虑其他代理人的限制政策的时间接近无穷大。具体来说,我们开发了一个新的优化目标,最大限度地提高每个代理的平均奖励直接占其行为的影响,其他代理将收敛到的政策限制。我们的论文在这个问题设置的特点理想的解决方案的概念,并提供了实用的方法,优化可能的结果。由于我们有远见的目标,我们在一套不同的多智能体基准领域中展示了比最先进的基线更好的长期性能。

英文摘要:

The main challenge of multiagent reinforcement learning is the difficulty of learning useful policies in the presence of other simultaneously learning agents whose changing behaviors jointly affect the environment's transition and reward dynamics. An effective approach that has recently emerged for addressing this non-stationarity is for each agent to anticipate the learning of other agents and influence the evolution of future policies towards desirable behavior for its own benefit. Unfortunately, previous approaches for achieving this suffer from myopic evaluation, considering only a finite number of policy updates. As such, these methods can only influence transient future policies rather than achieving the promise of scalable equilibrium selection approaches that influence the behavior at convergence. In this paper, we propose a principled framework for considering the limiting policies of other agents as time approaches infinity. Specifically, we develop a new optimization objective that maximizes each agent's average reward by directly accounting for the impact of its behavior on the limiting set of policies that other agents will converge to. Our paper characterizes desirable solution concepts within this problem setting and provides practical approaches for optimizing over possible outcomes. As a result of our farsighted objective, we demonstrate better long-term performance than state-of-the-art baselines across a suite of diverse multiagent benchmark domains.

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。

↑