Record Details

Risk-Constrained Markov Decision Processes

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title Risk-Constrained Markov Decision Processes
 
Creator BORKAR, V
JAIN, R
 
Subject Constrained Markov decision processes
risk measures
stochastic approximations
OPTIMIZATION
UNCERTAINTY
ALGORITHMS
 
Description We propose a new constrained Markov decision process framework with risk-type constraints. The risk metric we use is Conditional Value-at-Risk (CVaR), which is gaining popularity in finance. It is a conditional expectation but the conditioning is defined in terms of the level of the tail probability. We propose an iterative offline algorithm to find the risk-contrained optimal control policy. A two time-scale stochastic approximation-inspired 'learning' variant is also sketched, and its convergence proved to the optimal risk-constrained policy.
 
Publisher IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
 
Date 2014-12-28T14:24:49Z
2014-12-28T14:24:49Z
2014
 
Type Article
 
Identifier IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 59(9)2574-2579
0018-9286
1558-2523
http://dx.doi.org/10.1109/TAC.2014.2309262
http://dspace.library.iitb.ac.in/jspui/handle/100/16746
 
Language English