Collection
Theoretical Aspects of Reinforcement Learning (by invitation only)
Reinforcement learning (RL) is about learning and making optimal decisions in an unknown environment to obtain the maximum reward. Its ultimate purpose is to develop explainable/interpretable algorithms for optimal strategies in a data-driven way. It is one of the three fundamental machine learning paradigms, along-side supervised learning and unsupervised learning, and is at the crossroads of control, optimization, statistics and computer science. Recently there is an upsurge of interest and development in RL theory and applications in the communities of stochastic control, stochastic analysis, and financial engineering/mathematical finance. This special issue will bring leading researchers in these communities and showcase the latest research achievements in RL. The emphasis will be placed on fundamental and theoretical developments rather than off-the-shelf applications of existing RL algorithms.
Submission to this Special Issue is by invitation only.
Editors
-
Xin Guo
Department of Industrial Engineering and Operations Research University of California USA xinguo@ieor.berkeley.edu
-
Xunyu Zhou
Department of Industrial Engineering and Operations Research Columbia University USA xz2574@columbia.edu
