Name
Title | ||
|---|---|---|
An active-set strategy to solve Markov decision processes with good-deal risk measure |
Abstract | ||
|---|---|---|
This paper proposes a quasi closed-form solution for the reweighting of transition probabilities in finite state, finite action distributionally robust Markov decision processes with good-deal risk measure. The relation to the expected (risk-neutral) and minimax (worst-case) discounted cumulated cost objectives is discussed, as well as possible methods for the choice of the risk measure parameters. Numerical results illustrate the computational effectiveness of the proposed approach. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1007/s11590-019-01413-0 | Optimization Letters |
Keywords | Field | DocType |
Good-deal risk measure, Distributionally robust Markov decision process, Active-set, Second-order cone | Mathematical optimization,Minimax,Active set strategy,Markov decision process,Finite state,Risk measure,Mathematics | Journal |
Volume | Issue | ISSN |
13 | 6 | 1862-4472 |
Citations | PageRank | References |
0 | 0.34 | 14 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Shu Tu | 1 | 0 | 0.34 |
| Boris Defourny | 2 | 25 | 6.26 |