Preprint
Modified Policy Iteration for Exponential Cost Risk Sensitive MDPs
ArXiv.org
Cornell University
02/07/2023
DOI: 10.48550/arxiv.2302.03811
Abstract
Modified policy iteration (MPI) also known as optimistic policy iteration is at the core of many reinforcement learning algorithms. It works by combining elements of policy iteration and value iteration. The convergence of MPI has been well studied in the case of discounted and average-cost MDPs. In this work, we consider the exponential cost risk-sensitive MDP formulation, which is known to provide some robustness to model parameters. Although policy iteration and value iteration have been well studied in the context of risk sensitive MDPs, modified policy iteration is relatively unexplored. We provide the first proof that MPI also converges for the risk-sensitive problem in the case of finite state and action spaces. Since the exponential cost formulation deals with the multiplicative Bellman equation, our main contribution is a convergence proof which is quite different than existing results for discounted and risk-neutral average-cost problems. The proof of approximate modified policy iteration for risk sensitive MDPs is also provided in the appendix.
Details
- Title: Subtitle
- Modified Policy Iteration for Exponential Cost Risk Sensitive MDPs
- Creators
- Yashaswini MurthyMehrdad MoharramiR Srikant
- Resource Type
- Preprint
- Publication Details
- ArXiv.org
- DOI
- 10.48550/arxiv.2302.03811
- ISSN
- 2331-8422
- Publisher
- Cornell University
- Number of pages
- 30
- Language
- English
- Date posted
- 02/07/2023
- Academic Unit
- Computer Science
- Record Identifier
- 9984446695002771
Metrics
70 Record Views