arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1611.03071cs.LG
收藏

强化学习中的公平性

Fairness in Reinforcement Learning

University of Pennsylvania(宾夕法尼亚大学)

Shahin Jabbari, Matthew Joseph, Michael Kearns, Jamie Morgenstern, Aaron Roth

摘要:

我们开始研究强化学习中的公平性,其中学习算法的行为可能会影响其环境和未来的奖励。我们的公平性约束要求,如果选择后一个动作的长期(折扣)奖励更高,则算法永远不会偏好一个动作。第一个结果是否定的:尽管公平性与最优策略一致,但满足公平性的任何学习算法必须花费状态数量的时间指数,以实现对最优策略的非平凡近似。然后,我们提供了一个可证明公平的多项式时间算法下的近似公平的概念,从而建立一个指数差距之间的确切和近似公平

英文摘要:

We initiate the study of fairness in reinforcement learning, where the actions of a learning algorithm may affect its environment and future rewards. Our fairness constraint requires that an algorithm never prefers one action over another if the long-term (discounted) reward of choosing the latter action is higher. Our first result is negative: despite the fact that fairness is consistent with the optimal policy, any learning algorithm satisfying fairness must take time exponential in the number of states to achieve non-trivial approximation to the optimal policy. We then provide a provably fair polynomial time algorithm under an approximate notion of fairness, thus establishing an exponential gap between exact and approximate fairness

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。

↑