arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1902.04178cs.LGcs.AIstat.ML
收藏

随机强化学习

Stochastic Reinforcement Learning

Victoria University(维多利亚大学);Hong Kong Baptist University(香港浸会大学);University of California, San Diego(加州大学圣地亚哥分校)

Nikki Lijing Kuang, Clement H. C. Leung, Vienne W. K. Sung

摘要:

在强化学习中,奖励和惩罚通常是不确定的,并且总是有随机因素控制潜在的情况。这种随机因素往往很多,无法事先知道,而且它们往往会掩盖潜在的奖惩模式。事实上,如果没有随机因素,每次都会出现相同的结果,所涉及的学习问题可以大大简化。此外,在大多数实际情况下,观察获得奖励或惩罚的成本可能很大,人们希望通过产生最小成本来得出正确的学习结论。在本文中,我们提出了一个随机的方法来强化学习,明确建模的变化存在于学习环境和观察的成本。定量地分析了学习成功的准则和规则,并得到了超过观测成本界的概率。

英文摘要:

In reinforcement learning episodes, the rewards and punishments are often non-deterministic, and there are invariably stochastic elements governing the underlying situation. Such stochastic elements are often numerous and cannot be known in advance, and they have a tendency to obscure the underlying rewards and punishments patterns. Indeed, if stochastic elements were absent, the same outcome would occur every time and the learning problems involved could be greatly simplified. In addition, in most practical situations, the cost of an observation to receive either a reward or punishment can be significant, and one would wish to arrive at the correct learning conclusion by incurring minimum cost. In this paper, we present a stochastic approach to reinforcement learning which explicitly models the variability present in the learning environment and the cost of observation. Criteria and rules for learning success are quantitatively analyzed, and probabilities of exceeding the observation cost bounds are also obtained.

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。

↑