Abstract
Recent work on interactions among rational agents has put forward a computationally tractable, deduction-based scheme for automated agents to use in analyzing multiagent encounters. While the theory has defined irrational actions, it has underconstrained an agent's choices: there are many situations where an agent in the previous framework was faced with several potentially rational actions, and no way of choosing among them. This paper presents a probabilistic extension to the previous framework of Genesereth, Ginsberg, and Rosenschein [Genesereth et al. 1986] that provides agents with a mechanism for further refining their choice of rational moves. At the same time, it maintains the computational attractiveness of the previous approach.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have