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 1506.04514math.OC
收藏

具有基线保证的稳健策略Optimization

Robust Policy Optimization with Baseline Guarantees

Yinlam Chow, Marek Petrik, Mohammad Ghavamzadeh

摘要:

我们的目标是计算一个政策,保证改善回报超过基线政策,即使可用的MDP模型是不准确的。例如,当真实模型不可访问时,可以通过系统辨识技术来构造不准确的模型。当建模误差较大时,所构造模型的标准解相对于真实模型没有性能保证。在本文中,我们开发的算法,提供这样的性能保证,并显示其复杂性和保守性之间的权衡。我们新的基于模型的安全策略搜索算法利用了鲁棒优化技术的最新进展。此外,我们用一个数值例子来说明这些算法的有效性。

英文摘要:

Our goal is to compute a policy that guarantees improved return over a baseline policy even when the available MDP model is inaccurate. The inaccurate model may be constructed, for example, by system identification techniques when the true model is inaccessible. When the modeling error is large, the standard solution to the constructed model has no performance guarantees with respect to the true model. In this paper we develop algorithms that provide such performance guarantees and show a trade-off between their complexity and conservatism. Our novel model-based safe policy search algorithms leverage recent advances in robust optimization techniques. Furthermore we illustrate the effectiveness of these algorithms using a numerical example.

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。

↑