arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.12307cs.LGcs.AIcs.MA
收藏

合作竞争环境中理性偏好与非理性偏好的平衡

Balancing Rational and Other-Regarding Preferences in Cooperative-Competitive Environments

HSE University(高等经济大学);JetBrains Research(JetBrains研究院)

Dmitry Ivanov, Vladimir Egorov, Aleksei Shpilman

摘要:

最近的强化学习研究广泛探讨了混合环境中合作和竞争行为之间的相互作用。与合作环境中的代理人努力实现共同目标不同,混合环境因自私和社会利益的冲突而臭名昭着。因此,纯粹理性的行为者往往很难实现和维持合作。诱导合作行为的一种普遍方法是根据其他代理人的福利分配额外的奖励。然而,这种方法受到多代理信用分配的问题,这可能会阻碍性能。在协同设置中,QMIX和COMA等最先进的算法有效地缓解了这个问题。尽管如此,当应用于混合环境时,这些算法可能会导致不公平的奖励分配。我们提出了BAROCCO,这些算法的扩展能够平衡个人和社会的激励。BAROCCO背后的机制是训练两个不同但相互交织的组件,共同影响每个代理的决策。我们的元算法兼容Q学习和Actor-Critic框架。我们通过实验证实了现有方法的优势,并在两个混合的多智能体设置的行为方面的BAROCCO探索。

英文摘要:

Recent reinforcement learning studies extensively explore the interplay between cooperative and competitive behaviour in mixed environments. Unlike cooperative environments where agents strive towards a common goal, mixed environments are notorious for the conflicts of selfish and social interests. As a consequence, purely rational agents often struggle to achieve and maintain cooperation. A prevalent approach to induce cooperative behaviour is to assign additional rewards based on other agents' well-being. However, this approach suffers from the issue of multi-agent credit assignment, which can hinder performance. This issue is efficiently alleviated in cooperative setting with such state-of-the-art algorithms as QMIX and COMA. Still, when applied to mixed environments, these algorithms may result in unfair allocation of rewards. We propose BAROCCO, an extension of these algorithms capable to balance individual and social incentives. The mechanism behind BAROCCO is to train two distinct but interwoven components that jointly affect each agent's decisions. Our meta-algorithm is compatible with both Q-learning and Actor-Critic frameworks. We experimentally confirm the advantages over the existing methods and explore the behavioural aspects of BAROCCO in two mixed multi-agent setups.

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。

↑