all AI news
Sample-efficient Learning of Infinite-horizon Average-reward MDPs with General Function Approximation
April 22, 2024, 4:41 a.m. | Jianliang He, Han Zhong, Zhuoran Yang
cs.LG updates on arXiv.org arxiv.org
Abstract: We study infinite-horizon average-reward Markov decision processes (AMDPs) in the context of general function approximation. Specifically, we propose a novel algorithmic framework named Local-fitted Optimization with OPtimism (LOOP), which incorporates both model-based and value-based incarnations. In particular, LOOP features a novel construction of confidence sets and a low-switching policy updating scheme, which are tailored to the average-reward and function approximation setting. Moreover, for AMDPs, we propose a novel complexity measure -- average-reward generalized eluder coefficient …
abstract approximation arxiv confidence construction context cs.lg decision features framework function general horizon loop markov novel optimism optimization processes sample stat.ml study type value
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Consultant Senior Power BI & Azure - CDI - H/F
@ Talan | Lyon, France