Agent interaction in distributed POMDPs and its implications on complexity

The ability to coordinate effectively is critical for agents to accomplish their goals in a multi-agent system. A number of researchers have modeled the coordination problem for multi-agent systems using decision theory. The most general models have proven to be extremely complex to solve optimally (NEXP-complete). Some of the more restricted models have been much more tractable, though still difficult (NP-complete). What is missing is an understanding about why some models are much easier than others. This work fills this gap by providing a condition that distinguishes between problems in NP and those strictly harder than NP. This condition relates to the quantity of information each agent has about the others, and whether this information can be represented in a succinct way. We show that the class of problems that satisfy this condition is NP-complete. We illustrate this idea with two interaction protocols that satisfy the condition. For those problems that do not satisfy this condition we demonstrate how our theoretical results can be used to generate an NP approximation of the original problem.

[1]  Claudia V. Goldman,et al.  Optimizing information exchange in cooperative multi-agent systems , 2003, AAMAS '03.

[2]  Sridhar Mahadevan,et al.  Learning to Communicate and Act in Cooperative Multiagent Systems using Hierarchical Reinforcement Learning , 2004 .

[3]  Christos Papadimitriou,et al.  Intractable problems in control theory , 1985, 1985 24th IEEE Conference on Decision and Control.

[4]  John N. Tsitsiklis,et al.  On the Complexity of Designing Distributed Protocols , 1982, Inf. Control..

[5]  Victor R. Lesser,et al.  Decentralized Markov decision processes with event-driven interactions , 2004, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004..

[6]  Milind Tambe,et al.  The Communicative Multiagent Team Decision Problem: Analyzing Teamwork Theories and Models , 2011, J. Artif. Intell. Res..

[7]  Victor R. Lesser,et al.  Multi-agent policies: from centralized ones to decentralized ones , 2002, AAMAS '02.

[8]  Edmund H. Durfee,et al.  Multiagent planning for agents with internal execution resource constraints , 2003, AAMAS '03.

[9]  Kee-Eung Kim,et al.  Learning to Cooperate via Policy Search , 2000, UAI.

[10]  Claudia V. Goldman,et al.  Decentralized Control of Cooperative Systems: Categorization and Complexity Analysis , 2004, J. Artif. Intell. Res..

[11]  Victor R. Lesser,et al.  Minimizing communication cost in a distributed Bayesian network using a decentralized MDP , 2003, AAMAS '03.

[12]  Neil Immerman,et al.  The Complexity of Decentralized Control of Markov Decision Processes , 2000, UAI.

[13]  Victor R. Lesser,et al.  Analyzing myopic approaches for multi-agent communication , 2005, IEEE/WIC/ACM International Conference on Intelligent Agent Technology.

[14]  Claudia V. Goldman,et al.  Solving Transition Independent Decentralized Markov Decision Processes , 2004, J. Artif. Intell. Res..

[15]  Sridhar Mahadevan,et al.  Learning to communicate and act using hierarchical reinforcement learning , 2004, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004..