Verification of Markov Decision Processes with Risk-Sensitive Measures
–arXiv.org Artificial Intelligence
We develop a method for computing policies in Markov decision processes with risk-sensitive measures subject to temporal logic constraints. Specifically, we use a particular risk-sensitive measure from cumulative prospect theory, which has been previously adopted in psychology and economics. The nonlinear transformation of the probabilities and utility functions yields a nonlinear programming problem, which makes computation of optimal policies typically challenging. We show that this nonlinear weighting function can be accurately approximated by the difference of two convex functions. This observation enables efficient policy computation using convex-concave programming. We demonstrate the effectiveness of the approach on several scenarios.
arXiv.org Artificial Intelligence
Apr-19-2020
- Country:
- Europe > Denmark (0.04)
- North America > United States
- District of Columbia > Washington (0.04)
- Texas > Travis County
- Austin (0.04)
- New York > New York County
- New York City (0.04)
- Maryland > Prince George's County
- College Park (0.04)
- Genre:
- Research Report (0.64)
- Industry:
- Transportation (0.30)