Stochastic dominance-constrained Markov decision processes
From MaRDI portal
(Redirected from Publication:4920260)
Abstract: We are interested in risk constraints for infinite horizon discrete time Markov decision processes (MDPs). Starting with average reward MDPs, we show that increasing concave stochastic dominance constraints on the empirical distribution of reward lead to linear constraints on occupation measures. The optimal policy for the resulting class of dominance-constrained MDPs is obtained by solving a linear program. We compute the dual of this linear program to obtain average dynamic programming optimality equations that reflect the dominance constraint. In particular, a new pricing term appears in the optimality equations corresponding to the dominance constraint. We show that many types of stochastic orders can be used in place of the increasing concave stochastic order. We also carry out a parallel development for discounted reward MDPs with stochastic dominance constraints. The paper concludes with a portfolio optimization example.
Recommendations
- Stochastic Dynamic Optimization with Discounted Stochastic Dominance Constraints
- Optimization with Stochastic Dominance Constraints
- A convex analytic approach to risk-aware Markov decision processes
- Stochastic dominance for sequences and implied utility in dynamic optimization
- Constrained Undiscounted Stochastic Dynamic Programming
Cited in
(14)- Indices for families of competing Markov decision processes with influence
- Modeling stochastic dominance as infinite-dimensional constraint systems via the Strassen theorem
- Multi-stage portfolio selection problem with dynamic stochastic dominance constraints
- Aspects of optimization with stochastic dominance
- Markov decision problems where means bound variances
- Primal-dual algorithms for optimization with stochastic dominance
- Stochastic Dynamic Optimization with Discounted Stochastic Dominance Constraints
- Ordinal decision models for Markov decision processes
- Risk-sensitive semi-Markov decision processes with general utilities and multiple criteria
- A convex analytic approach to risk-aware Markov decision processes
- Interval dominance based structural results for Markov decision process
- Joint chance-constrained Markov decision processes
- Relaxation of stochastic dominance constraints via optimal mass transport
- Relations between risk-averse models in extended two-stage stochastic optimization
This page was built for publication: Stochastic dominance-constrained Markov decision processes
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4920260)
