Markov Decision Processes with Risk-Sensitive Criteria: An Overview
arXiv:2311.06896 · doi:10.1007/s00186-024-00857-0
Abstract
The paper provides an overview of the theory and applications of risk-sensitive Markov decision processes. The term 'risk-sensitive' refers here to the use of the Optimized Certainty Equivalent as a means to measure expectation and risk. This comprises the well-known entropic risk measure and Conditional Value-at-Risk. We restrict our considerations to stationary problems with an infinite time horizon. Conditions are given under which optimal policies exist and solution procedures are explained. We present both the theory when the Optimized Certainty Equivalent is applied recursively as well as the case where it is applied to the cumulated reward. Discounted as well as non-discounted models are reviewed
References in corpus (10)
- Average optimality for risk-sensitive control with general state space
- Risk-sensitive Markov control processes
- Stochastic Optimal Growth Model with Risk Sensitive Preferences
- Markov Decision Processes with Recursive Risk Measures
- Partially Observable Risk-Sensitive Markov Decision Processes
- A recursive algorithm for multivariate risk measures and a set-valued Bellman's principle
- A Characterization of the optimal risk-Sensitive average cost in finite controlled Markov chains
- Risk-Sensitive Dividend Problems
- Risk-Sensitive Control and an Abstract Collatz-Wielandt Formula
- Discrete-time risk-aware optimal switching with non-adapted costs