Constrained Risk-Averse Markov Decision Processes
Autor: | Ahmadi, Mohamadreza, Rosolia, Ugo, Ingham, Michel D., Murray, Richard M., Ames, Aaron D. |
---|---|
Rok vydání: | 2021 |
Předmět: |
FOS: Computer and information sciences
Computer Science - Robotics Artificial Intelligence (cs.AI) Optimization and Control (math.OC) Computer Science - Artificial Intelligence FOS: Electrical engineering electronic engineering information engineering FOS: Mathematics Systems and Control (eess.SY) General Medicine Robotics (cs.RO) Electrical Engineering and Systems Science - Systems and Control Mathematics - Optimization and Control |
Zdroj: | Proceedings of the AAAI Conference on Artificial Intelligence. 35:11718-11725 |
ISSN: | 2374-3468 2159-5399 |
Popis: | We consider the problem of designing policies for Markov decision processes (MDPs) with dynamic coherent risk objectives and constraints. We begin by formulating the problem in a Lagrangian framework. Under the assumption that the risk objectives and constraints can be represented by a Markov risk transition mapping, we propose an optimization-based method to synthesize Markovian policies that lower-bound the constrained risk-averse problem. We demonstrate that the formulated optimization problems are in the form of difference convex programs (DCPs) and can be solved by the disciplined convex-concave programming (DCCP) framework. We show that these results generalize linear programs for constrained MDPs with total discounted expected costs and constraints. Finally, we illustrate the effectiveness of the proposed method with numerical experiments on a rover navigation problem involving conditional-value-at-risk (CVaR) and entropic-value-at-risk (EVaR) coherent risk measures. Draft Accepted for Presentation at The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), Feb. 2-9, 2021 |
Databáze: | OpenAIRE |
Externí odkaz: |