Learning agents can improve performance cooperating with other agents, particularly learning agents forming a committee outperform individual agents. This "ensemble effect&qu...
Multi-Agent Reinforcement Learning (MARL) algorithms suffer from slow convergence and even divergence, especially in large-scale systems. In this work, we develop a supervision fr...
Chongjie Zhang, Sherief Abdallah, Victor R. Lesser
The `Cooperation Logic of Propositional Control', cl-pc, of van der Hoek and Wooldridge is a logic for reasoning about the ability of agents and groups of agents to obtain a ...
Agents can benefit from contracting some of their tasks that cannot be performedby themselves or that can be performed moreefficiently by other agents. Developing an agent's ...
This paper presents a general architecture towards a more generic approach to conversational agents. Our architecture contains generic (in sense of application independent) natura...