资源分类
》 资源 》论文》Regret Bounds for Learning State Representations in Reinforcement Learning

Regret Bounds for Learning State Representations in Reinforcement Learning

2020-02-26 | |  43 |   36 |   0

Abstract

We consider the problem of online reinforcement learning when several state representations (mapping histories to a discrete state space) are available to the learning agent. At least one of these representations is assumed to induce a Markov decision process (MDP), and the performance of the agent is measured in terms of cumulative regret against the optimal policy giving the highest average reward in this MDP representation. We propose an algorithm (U CB -M S) with 图片.png regret in any communicating MDP. The regret bound shows that U CB -M S automatically adapts to the Markov model and improves over the currently known best bound of order 图片.png

上一篇：Robust exploration in linear quadratic reinforcement learning

下一篇：Learner-aware Teaching: Inverse Reinforcement Learning with Preferences and Constraints

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...