arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1005.1860cs.AI
收藏

马尔可夫决策过程近似线性规划的正则化特征选择

Feature Selection Using Regularization in Approximate Linear Programs for Markov Decision Processes

University of Massachusetts, Amherst(马萨诸塞大学阿默斯特分校);Duke University(杜克大学)

Marek Petrik, Gavin Taylor, Ron Parr, Shlomo Zilberstein

摘要:

近似动态规划已成功地应用于各种领域,但它依赖于一小部分提供的近似特征来可靠地计算解。由于样本数量有限,大量丰富的特征集可能会导致现有算法过拟合。我们使用$L_1$正则化近似线性规划来解决这个缺点。由于所提出的方法可以自动选择适当的丰富度的功能,其性能不会降低随着越来越多的功能。这些结果依赖于新的和更强的采样范围的正则化近似线性规划。我们还提出了一个计算效率高的同伦方法。实验结果表明,该方法在简单的MDP和标准基准问题上表现良好。

英文摘要:

Approximate dynamic programming has been used successfully in a large variety of domains, but it relies on a small set of provided approximation features to calculate solutions reliably. Large and rich sets of features can cause existing algorithms to overfit because of a limited number of samples. We address this shortcoming using $L_1$ regularization in approximate linear programming. Because the proposed method can automatically select the appropriate richness of features, its performance does not degrade with an increasing number of features. These results rely on new and stronger sampling bounds for regularized approximate linear programs. We also propose a computationally efficient homotopy method. The empirical evaluation of the approach shows that the proposed method performs well on simple MDPs and standard 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。

↑