We adopt the decision-theoretic principle of expected utility maximization as a paradigm for designing autonomous rational agents operating in multi-agent environments. We use the...
Multiagent environments are often not cooperative nor collaborative; in many cases, agents have conflicting interests, leading to adversarial interactions. This paper presents a ...
Inon Zuckerman, Sarit Kraus, Jeffrey S. Rosenschei...
Abstract. In multi-agent reinforcement learning systems, it is important to share a reward among all agents. We focus on the Rationality Theorem of Profit Sharing [5] and analyze ...
We propose a general framework to represent changes in the mental state of a rational agent due to the acquisition of new information and/or to the arising of new desires; fundamen...
We present a utility-driven rationality and a complementary-driven rationality based model, relative to multiple partner coalitions, motivated by relations of dependence and instru...