Learning in many multi-agent settings is inherently repeated play. This calls into question the naive application of single play Nash equilibria in multi-agent learning and sugges...
Discussions of agent interactions frequently characterize behavior as “coherent,” “collaborative,” “cooperative,” “competitive,” or “coordinated.” We propose a...
H. Van Dyke Parunak, Sven Brueckner, Mitchell Flei...
Abstract. We study safety level coalitions in competitive games. Given a normal form game, we define a corresponding cooperative game with transferable utility, where the value of ...
Yoram Bachrach, Maria Polukarov, Nicholas R. Jenni...
Since Holland (1993) introduced the concept of tags as a possible cooperation forming mechanism in evolving system (among other things) a number of tag models with intriguing, and ...
Abstract- Behavior based architectures have many parameters that must be tuned to produce effective and believable agents. We use genetic algorithms to tune simple behavior based c...
Ryan E. Leigh, Tony Morelli, Sushil J. Louis, Moni...