ITR: Decision Making, Optimization, Learning, and Adaptation in Uncertain and Dynamic Environments

点击翻译按钮获取中文摘要

PROJECT SUMMARYThis project deals with decision making,optimization,learning,and adaptation in uncertainand dynamic environments.The main objectives are:(a)To develop e .cient learning methods (either simulation-based or on-line)for construct-ing near-optimal policies for dynamic decision making in uncertain environments.(b)To develop new methods and to enhance the understanding of certain existing methodsfor addressing large scale dynamic decision-making problems.(c)To develop computational methods and learning algorithms that pertain to risk-sensitiveperformance criteria,as well as fundamental limitations in the form of computationalcomplexity results.(d)To establish the fundamental limitations of learning in multi-armed bandit problemsand Markov decision processes (MDPs),in the form of lower bounds on the amount oflearning that is required,and simultaneously derive optimal algorithms whose require-ments match the lower bounds.(e)To develop new formulations,models,and algorithms for multi-agent learning andadaptation in dynamic environments.The proposed research involves problems that are both practically relevant and intellec-tually deep.On the application side,the range of relevant contexts is vast.It includes logistics(e.g.,supply chain management,inventory control,.eet assignment),manufacturing systems(e.g.,sequencing and scheduling),communications (e.g.,frequency allocation and hando .management in wireless systems,routing and congestion control),.nance,robotics,andeconomic systems (e.g.,auctions and real-time markets).The intellectual merit arises because some of the problems present signi .cant mathe-matical challenges,that require new approaches as well as new problem formulations.Thisproject will lead to advances in the scienti .c knowledge-base and the state of the art inthe .eld of decision making.In addition,this research combines methods from operationsresearch and control theory (dynamic programming),applied probability (stochastic approx-imation and large deviations),arti .cial intelligence (learning),and economics (game theory).As such,a broader impact of this work will be the advancement of the cross-fertilization ofthese disciplines.In more concrete terms,this cross-fertilization will occur not only throughpublications,but also through presentations at audiences from disparate communities (e.g.,at machine learning as well as control theory conferences),and also through the developmentof new courses.Finally,at the human resource and training level,the most direct impactwill occur through the mentoring of doctoral students,who will be expected to populateleading academic institutions.1