Risk-Constrained Markov Decision Processes
DSpace at IIT Bombay
View Archive InfoField | 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
|
|