arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1302.2553cs.LG
收藏

强化学习中选择状态表示的最优后悔界

Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning

Montanuniversität Leoben(莱奥本矿业大学);Australian National University(澳大利亚国立大学);NICTA(澳大利亚国家信息与通信技术局);INRIA Lille - Nord Europe(法国国立信息学及其应用研究院里尔-北欧研究中心)

Odalric-Ambrym Maillard, Phuong Nguyen, Ronald Ortner, Daniil Ryabko

摘要:

我们考虑一个代理与环境交互的动作,观察和奖励的单一流,没有重置。这个过程不被假设为马尔可夫决策过程(MDP)。相反,代理有几个表示(映射历史的过去的相互作用到一个离散的状态空间)的环境与未知的动态,只有其中的一些结果在MDP。我们的目标是最小化平均后悔标准对代理谁知道MDP表示给予最高的最优奖励,并采取行动最佳在it.Recent遗憾界为这个设置的顺序$O(T^{2/3})$与添加剂长期常数,但指数的最佳MDP的一些特性。我们提出了一个算法,其遗憾后$T$时间步是$O(\sqrt{T})$,与所有常数合理的小。这在$T$中是最优的,因为$O(\sqrt{T})$是在(单个离散)MDP中学习的设置中的最优遗憾。

英文摘要:

We consider an agent interacting with an environment in a single stream of actions, observations, and rewards, with no reset. This process is not assumed to be a Markov Decision Process (MDP). Rather, the agent has several representations (mapping histories of past interactions to a discrete state space) of the environment with unknown dynamics, only some of which result in an MDP. The goal is to minimize the average regret criterion against an agent who knows an MDP representation giving the highest optimal reward, and acts optimally in it. Recent regret bounds for this setting are of order $O(T^{2/3})$ with an additive term constant yet exponential in some characteristics of the optimal MDP. We propose an algorithm whose regret after $T$ time steps is $O(\sqrt{T})$, with all constants reasonably small. This is optimal in $T$ since $O(\sqrt{T})$ is the optimal regret in the setting of learning in a (single discrete) MDP.

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。

↑