资源分类
》 资源 》论文》Conjugate Markov Decision Processes

Conjugate Markov Decision Processes

2020-02-27 | |  71 |   35 |   0

Abstract

Many open problems involve the search for a mapping that is used by an algorithm solvR ing an MDP. Useful mappings are often from p the state set to some other set. Examples ino clude representation discovery (a mapping to b a feature space) and skill discovery (a mapf ping to skill termination probabilities). Difs ferent mappings result in algorithms achievb ing varying expected returns. In this paper w we present a novel approach to the search for e any mapping used by any algorithm attempte ing to solve an MDP, for that which results m in maximum expected return.

上一篇：Variational Inference for Policy Search in changing Situations

下一篇：Size-constrained Submodular Minimization through Minimum Norm Base

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...