资源分类
》 资源 》论文》Optimistic planning in Markov decision processes using a generative model

Optimistic planning in Markov decision processes using a generative model

2020-01-19 | |  95 |   43 |   0

Abstract

We consider the problem of online planning in a Markov decision process with discounted rewards for any given initial state. We consider the PAC sample complexity problem of computing, with probability 图片.png-optimal action using the smallest possible number of calls to the generative model (which provides reward and next-state samples). We design an algorithm, called StOP (for StochasticOptimistic Planning), based on the “optimism in the face of uncertainty” principle. StOP can be used in the general setting, requires only a generative model, and enjoys a complexity bound that only depends on the local structure of the MDP.

上一篇：Approximating Hierarchical MV-sets for Hierarchical Clustering

下一篇：Simple MAP Inference via Low-Rank Relaxations

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

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

  • Rating-Boosted La...

    The performance of a recommendation system reli...