arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1104.4664cs.LG
收藏

时间二次差迹

Temporal Second Difference Traces

University of Michigan(密歇根大学)

Mitchell Keith Bloch

摘要:

Q学习是一种可靠但低效的非策略时间差方法,每次只支持一步奖励。使用近因启发法替换跟踪更有效,但可靠性较低。在这项工作中,我们介绍了无模型,非政策的时间差方法,更好地利用经验比沃特金斯的Q(λ)。我们引入了乐观Q(λ)和时间二阶差分迹(TSDT)。TSDT在确定性领域中特别强大。TSDT既不使用新近度也不使用频率分类,而是存储(s,a,r,s ',δ),以便在采取明显次优的动作之后可以执行非策略更新。在使用状态抽象时,如在MAXQ中,还有其他优点。我们证明了TSDT在确定性悬崖行走域中明显优于Q学习和Watkins的Q(λ)。噪声悬崖行走域中的结果对于TSDT来说不太有利,但证明了乐观Q(λ)的有效性,这是一种具有TSDT一些优点的替代迹线。

英文摘要:

Q-learning is a reliable but inefficient off-policy temporal-difference method, backing up reward only one step at a time. Replacing traces, using a recency heuristic, are more efficient but less reliable. In this work, we introduce model-free, off-policy temporal difference methods that make better use of experience than Watkins' Q(λ). We introduce both Optimistic Q(λ) and the temporal second difference trace (TSDT). TSDT is particularly powerful in deterministic domains. TSDT uses neither recency nor frequency heuristics, storing (s,a,r,s',δ) so that off-policy updates can be performed after apparently suboptimal actions have been taken. There are additional advantages when using state abstraction, as in MAXQ. We demonstrate that TSDT does significantly better than both Q-learning and Watkins' Q(λ) in a deterministic cliff-walking domain. Results in a noisy cliff-walking domain are less advantageous for TSDT, but demonstrate the efficacy of Optimistic Q(λ), a replacing trace with some of the advantages of TSDT.

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。

↑