Classically, an approach to the multiagent policy learning supposed that the agents, via interactions and/or by using preliminary knowledge about the reward functions of all playe...
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...
Stochastic games are a generalization of MDPs to multiple agents, and can be used as a framework for investigating multiagent learning. Hu and Wellman (1998) recently proposed a m...
This paper extends the link between evolutionary game theory and multi-agent reinforcement learning to multistate games. In previous work, we introduced piecewise replicator dynam...
Due to the non-stationary environment, learning in multi-agent systems is a challenging problem. This paper first introduces a new gradient-based learning algorithm, augmenting th...