Risk-Sensitive and Minimax Control of Discrete-Time, Finite-State Markov Decision Processes
Coraluppi, Stephano P.
Marcus, Steven I.
MetadataShow full item record
This paper analyzes a connection between risk-sensitive and minimaxcriteria for discrete-time, finite-states Markov Decision Processes(MDPs). We synthesize optimal policies with respect to both criteria,both for finite horizon and discounted infinite horizon problems. Ageneralized decision-making framework is introduced, which includes asspecial cases a number of approaches that have been considered in theliterature. The framework allows for discounted risk-sensitive andminimax formulations leading to stationary optimal policies on theinfinite horizon. We illustrate our results with a simple machinereplacement problem.
Showing items related by title, author, creator and subject.
Adaptive Control of Nonlinear Systems with Applications to Flight Control Systems and Suspension Dynamics Ghanadan, Reza (1993)In this dissertation, we employ recent theoretical advances in differential geometric formulation of nonlinear control theory and adaptive control to develop a practical adaptive nonlinear control strategy.<P>We first ...
Fernandez-Gaucherand, Emmanuel; Arapostathis, Aristotle; Marcus, Steven I. (1991)We consider an adaptive finite state controlled Markov chain with partial state information, motivated by a class of replacement problems. We present parameter estimation techniques based on the information available after ...
Kolos, K.R.; Tu, L.Q.; Vanegas, R.; Wardak, K.R. (1991)The control of surface quality during machining is an area in manufacturing which has recently received a great deal of attention in the field of research and development. The main objective of this project is to briefly ...