Journal
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
Volume 59, Issue 9, Pages 2574-2579Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TAC.2014.2309262
Keywords
Constrained Markov decision processes; risk measures; stochastic approximations
Funding
- NSF [IIS-0917410]
- NSF CAREER Award [CNS-0954116]
- ONR Young Investigator Award [N000141210766]
- Direct For Computer & Info Scie & Enginr
- Division Of Computer and Network Systems [0954116] Funding Source: National Science Foundation
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available