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 1906.01772cs.LGstat.ML
收藏

当所有动作不总是可用时的强化学习

Reinforcement Learning When All Actions are Not Always Available

University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校);Adobe Research(奥多比研究院)

Yash Chandak, Georgios Theocharous, Blossom Metevier, Philip S. Thomas

摘要:

马尔可夫决策过程(MDP)制定用于模拟许多现实世界的顺序决策问题,并没有有效地捕捉设置在每个时间步的可用决策(行动)的集合是随机的。最近,随机行动集马尔可夫决策过程(SAS-MDP)制定已被提出,它更好地捕捉的概念,随机行动集。在本文中,我们认为,现有的RL算法SAS-MDP可能会受到潜在的分歧问题,并提出新的策略梯度算法SAS-MDP,将方差降低技术独特的设置,并提供其收敛的条件。最后,我们通过实验证明了我们的方法在任务上的实用性,这些任务是由现实生活中的用例激发的,其中动作集是随机的。

英文摘要:

The Markov decision process (MDP) formulation used to model many real-world sequential decision making problems does not efficiently capture the setting where the set of available decisions (actions) at each time step is stochastic. Recently, the stochastic action set Markov decision process (SAS-MDP) formulation has been proposed, which better captures the concept of a stochastic action set. In this paper we argue that existing RL algorithms for SAS-MDPs can suffer from potential divergence issues, and present new policy gradient algorithms for SAS-MDPs that incorporate variance reduction techniques unique to this setting, and provide conditions for their convergence. We conclude with experiments that demonstrate the practicality of our approaches on tasks inspired by real-life use cases wherein the action set is stochastic.

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。

↑