Market Based Resource Allocation with Incomplete Information

Bo An, Chunyan Miao, Zhiqi Shen

Although there are some research efforts toward resource allocation in multi-agent systems (MAS), most of these work assume that each agent has complete information about other agents. This research investigates interactions among selfish, rational, and autonomous agents in resource allocation, each with incomplete information about other entities, and each seeking to maximize its expected utility. This paper presents a proportional resource allocation mechanism and gives a game theoretical analysis of the optimal strategies and the analysis shows the existence of equilibrium in the incomplete information setting. By augmenting the resource allocation mechanism with a deal optimization mechanism, trading agents can be programmed to optimize resource allocation results by updating beliefs and resubmitting bids. Experimental results showed that by having a deal optimization stage, the resource allocation mechanism produced generally optimistic outcomes (close to market equilibrium).