Graphical Models in Local, Asymmetric Multi-Agent Markov Decision Processes

In multi-agent MDPs, it is generally necessary to consider the joint state space of all agents, making the size of the problem and the solution exponential in the number of agents. However, often interactions between the agents are only local, which suggests a more compact problem representation. We consider a subclass of multi-agent MDPs with local interactions where dependencies between agents are asymmetric, meaning that agents can affect others in a unidirectional manner. This asymmetry, which often occurs in domains with authority-driven relationships between agents, allows us to make better use of the locality of agents’ interactions. We present and analyze a graphical model of such problems and show that, for some classes of problems, it can be exploited to yield significant (sometimes exponential) savings in problem and solution size, as well as in computational efficiency of solution algorithms.

• Type: Conference
• Year: 2004
• Where: ATAL
• Authors: Dmitri A. Dolgov, Edmund H. Durfee
• Keywords: ATAL 2004, Compact Problem Representation, Joint State Space, Multi-agent Mdps