资源分类
》 资源 》论文》The Sample-Complexity of General Reinforcement Learning

The Sample-Complexity of General Reinforcement Learning

2020-03-03 | |  230 |   45 |   0

Abstract

We present a new algorithm for general reinforcement learning where the true environment is known to belong to a finite class of N arbitrary models. The algorithm is shown to be near-optimal for all but 图片.png timesteps with high probability. Infinite classes are also considered where we show that compactness is a key criterion for determining the existence of uniform sample-complexity bounds. A matching lower bound is given for the finite case.

上一篇：Concurrent Reinforcement Learning from Customer Interactions

下一篇：Online Feature Selection for Model-based Reinforcement Learning

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 ...

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

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