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 1206.6485cs.LGstat.ML
收藏

稀疏强化学习的贪心算法

Greedy Algorithms for Sparse Reinforcement Learning

Duke University(杜克大学)

Christopher Painter-Wakefield, Ronald Parr

摘要:

在强化学习(RL)社区努力扩大RL的范围和适用性的过程中,特征选择和正则化正成为越来越重要的工具。解决特征选择问题的一种方法是在学习方法上施加稀疏诱导形式的正则化。最近关于$L_1$正则化的工作采用了监督学习文献中的技术,用于RL。另一种在监督学习社区中重新受到关注的方法是使用一种简单的算法,该算法可以增加新的功能。这种算法具有$L_1$正则化方法的许多良好特性,同时也非常有效,并且在某些情况下,允许从采样数据恢复稀疏目标函数的真实形式的理论保证。本文考虑正交匹配追踪(OMP)的变体应用于强化学习。实验分析和比较现有的$L_1$正则化方法的算法。我们证明,也许是最自然的情况下,人们可能希望实现稀疏恢复失败,然而,一个变种,OMP-BRM,提供了有前途的理论保证在某些假设下的特征字典。另一种变体OMP-TD在几个基准问题上的近似精度和效率方面都优于以前的方法。

英文摘要:

Feature selection and regularization are becoming increasingly prominent tools in the efforts of the reinforcement learning (RL) community to expand the reach and applicability of RL. One approach to the problem of feature selection is to impose a sparsity-inducing form of regularization on the learning method. Recent work on $L_1$ regularization has adapted techniques from the supervised learning literature for use with RL. Another approach that has received renewed attention in the supervised learning community is that of using a simple algorithm that greedily adds new features. Such algorithms have many of the good properties of the $L_1$ regularization methods, while also being extremely efficient and, in some cases, allowing theoretical guarantees on recovery of the true form of a sparse target function from sampled data. This paper considers variants of orthogonal matching pursuit (OMP) applied to reinforcement learning. The resulting algorithms are analyzed and compared experimentally with existing $L_1$ regularized approaches. We demonstrate that perhaps the most natural scenario in which one might hope to achieve sparse recovery fails; however, one variant, OMP-BRM, provides promising theoretical guarantees under certain assumptions on the feature dictionary. Another variant, OMP-TD, empirically outperforms prior methods both in approximation accuracy and efficiency on several benchmark problems.

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。

↑