资源分类
》 资源 》论文》Measuring Structural Similarities in Finite MDPs

Measuring Structural Similarities in Finite MDPs

2019-10-09 | |  88 |   48 |   0
Abstract In this paper, we investigate the structural similarities within a finite Markov decision process (MDP). We view a finite MDP as a heterogeneous directed bipartite graph and propose novel measures for the state and action similarities, in a mutually reinforced manner. We prove that the state similarity is a metric and the action similarity is a pseudometric. We also establish the connection between the proposed similarity measures and the optimal values of the MDP. Extensive experiments show that the proposed measures are effective

上一篇：Low-Bit Quantization for Attributed Network Representation Learning

下一篇：Multi-scale Information Diffusion Prediction with Reinforced Recurrent Networks

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...