An Optimality Principle for Concurrent Systems

Abstract. This paper presents a formulation of an optimality principle for a new class of concurrent decision systems formed by products of deterministic Markov decision processes (MDPs). For a single MDP, the optimality principle reduces to the usual Bellman's equation. The formulation is significant because it provides a basis for the development of optimisation algorithms for decentralised decision systems including a recently proposed method based on Petri Net unfoldings.

• Type: Conference
• Year: 2008
• Where: AUSAI
• Authors: Langford B. White, Sarah L. Hickmott
• Keywords: Artificial Intelligence, AUSAI 2008, Decision Systems, Deterministic Markov Decision, Optimality Principle