arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.07905cs.LGmath.OCstat.ML
收藏

基于Supergraphs的政策评估

Empirical Policy Evaluation with Supergraphs

University of Texas at Austin(德克萨斯大学奥斯汀分校);University of Michigan(密歇根大学)

Daniel Vial, Vijay Subramanian

摘要:

我们设计并分析了强化学习中经验策略评估问题的算法。我们的算法从高成本状态向后探索,以找到高价值的状态,而不是从所有状态向前工作的向前方法。虽然有几篇论文已经证明了向后探索经验的效用,我们进行了严格的分析表明,我们的算法可以降低平均情况下的样本复杂度从$O(S \log S)$低至$O(\log S)$。

英文摘要:

We devise and analyze algorithms for the empirical policy evaluation problem in reinforcement learning. Our algorithms explore backward from high-cost states to find high-value ones, in contrast to forward approaches that work forward from all states. While several papers have demonstrated the utility of backward exploration empirically, we conduct rigorous analyses which show that our algorithms can reduce average-case sample complexity from $O(S \log S)$ to as low as $O(\log S)$.

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。

↑