arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1701.08810stat.MLcs.AIcs.LGmath.OC
收藏

强化学习算法选择

Reinforcement Learning Algorithm Selection

Microsoft Research Maluuba(微软研究院 Maluuba);Orange Labs(Orange 实验室)

Romain Laroche, Raphael Feraud

摘要:

本文形式化了强化学习背景下的在线算法选择问题。设置如下所示:给定一个情节任务和有限数量的非策略RL算法,元算法必须决定在下一个情节期间哪个RL算法处于控制中,以便最大化预期回报。本文提出了一种新的元算法,称为时代随机强盗算法选择(ESBAS)。它的原理是在每个时期冻结策略更新,并留下一个重新启动的随机强盗负责算法选择。在一定的假设条件下,充分的理论分析表明,考虑到结构抽样预算的限制,它的近最优性。ESBAS首先在对话任务上进行经验评估,在大多数配置中,它表现出优于每个单独的算法。然后ESBAS适应真正的在线设置,算法在每次转换后更新其策略,我们称之为SSBAS。SSBAS的水果收集任务,它被证明是适应步长参数更有效地比经典的双曲衰减,并在雅达利游戏,它提高了性能的大幅提高。

英文摘要:

This paper formalises the problem of online algorithm selection in the context of Reinforcement Learning. The setup is as follows: given an episodic task and a finite number of off-policy RL algorithms, a meta-algorithm has to decide which RL algorithm is in control during the next episode so as to maximize the expected return. The article presents a novel meta-algorithm, called Epochal Stochastic Bandit Algorithm Selection (ESBAS). Its principle is to freeze the policy updates at each epoch, and to leave a rebooted stochastic bandit in charge of the algorithm selection. Under some assumptions, a thorough theoretical analysis demonstrates its near-optimality considering the structural sampling budget limitations. ESBAS is first empirically evaluated on a dialogue task where it is shown to outperform each individual algorithm in most configurations. ESBAS is then adapted to a true online setting where algorithms update their policies after each transition, which we call SSBAS. SSBAS is evaluated on a fruit collection task where it is shown to adapt the stepsize parameter more efficiently than the classical hyperbolic decay, and on an Atari game, where it improves the performance by a wide margin.

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。

↑