Product Distribution (PD) theory is a new framework for controlling Multi-Agent Systems (MAS’s). First we review one motivation of PD theory, as the information-theoretic extens...
We introduce relational temporal difference learning as an effective approach to solving multi-agent Markov decision problems with large state spaces. Our algorithm uses temporal ...
Cooperative multi-agent systems are ones in which several agents attempt, through their interaction, to jointly solve tasks or to maximize utility. Due to the interactions among t...
We present Policy Gradient Actor-Critic (PGAC), a new model-free Reinforcement Learning (RL) method for creating limited-memory stochastic policies for Partially Observable Markov ...
In this paper we describe an integrated multilevel learning approach to multiagent coalition formation in a real-time environment. In our domain, agents negotiate to form teams to...