Efficient Querying for Cooperative Probabilistic Commitments


  • Qi Zhang University of South Carolina
  • Edmund H. Durfee University of Michigan
  • Satinder Singh University of Michigan


Coordination and Collaboration, Multiagent Planning, Planning with Markov Models (MDPs, POMDPs), Agent Communication


Multiagent systems can use commitments as the core of a general coordination infrastructure, supporting both cooperative and non-cooperative interactions. Agents whose objectives are aligned, and where one agent can help another achieve greater reward by sacrificing some of its own reward, should choose a cooperative commitment to maximize their joint reward. We present a solution to the problem of how cooperative agents can efficiently find an (approximately) optimal commitment by querying about carefully-selected commitment choices. We prove structural properties of the agents' values as functions of the parameters of the commitment specification, and develop a greedy method for composing a query with provable approximation bounds, which we empirically show can find nearly optimal commitments in a fraction of the time methods that lack our insights require.




How to Cite

Zhang, Q., Durfee, E. H., & Singh, S. (2021). Efficient Querying for Cooperative Probabilistic Commitments. Proceedings of the AAAI Conference on Artificial Intelligence, 35(13), 11378-11386. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17356



AAAI Technical Track on Multiagent Systems