arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.01891cs.LGstat.ML
收藏

情景强化学习中乐观主义的统一观点

A Unifying View of Optimism in Episodic Reinforcement Learning

Universitat Pompeu Fabra(庞培法布拉大学);Barcelona Graduate School of Economics(巴塞罗那经济学研究生院);Imperial College London(帝国理工学院)

Gergely Neu, Ciara Pike-Burke

摘要:

面对不确定性时的乐观原则是许多理论上成功的强化学习算法的基础。在本文中,我们提供了一个通用的框架,设计,分析和实现这样的算法在情节强化学习问题。这个框架是建立在拉格朗日对偶,并证明了每一个模型乐观算法,构造一个乐观的MDP有一个等价的表示作为一个值乐观的动态规划算法。通常,人们认为这两类算法是不同的,模型乐观算法受益于更清晰的概率分析,而值乐观算法更容易实现,因此更实用。在本文中开发的框架,我们表明,它是可以得到最好的两个世界,通过提供一类算法,具有计算效率的动态编程实现,也是一个简单的概率分析。除了能够在表格设置中捕获许多现有的算法之外,我们的框架还可以在可实现的函数近似下解决大规模问题,其中它可以对最近提出的一些方法进行简单的基于模型的分析。

英文摘要:

The principle of optimism in the face of uncertainty underpins many theoretically successful reinforcement learning algorithms. In this paper we provide a general framework for designing, analyzing and implementing such algorithms in the episodic reinforcement learning problem. This framework is built upon Lagrangian duality, and demonstrates that every model-optimistic algorithm that constructs an optimistic MDP has an equivalent representation as a value-optimistic dynamic programming algorithm. Typically, it was thought that these two classes of algorithms were distinct, with model-optimistic algorithms benefiting from a cleaner probabilistic analysis while value-optimistic algorithms are easier to implement and thus more practical. With the framework developed in this paper, we show that it is possible to get the best of both worlds by providing a class of algorithms which have a computationally efficient dynamic-programming implementation and also a simple probabilistic analysis. Besides being able to capture many existing algorithms in the tabular setting, our framework can also address largescale problems under realizable function approximation, where it enables a simple model-based analysis of some recently proposed methods.

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。

↑