We describe a system that successfully transfers value function knowledge across multiple subdomains of realtime strategy games in the context of multiagent reinforcement learning....
Introspection mechanisms are employed in agent architectures to improve agent performance. However, there is currently no approach to introspection that makes automatic adjustment...
Evan A. Krause, Paul W. Schermerhorn, Matthias Sch...
Typically agent evaluation is done through Monte Carlo estimation. However, stochastic agent decisions and stochastic outcomes can make this approach inefficient, requiring many s...
Michael H. Bowling, Michael Johanson, Neil Burch, ...
We introduce a framework for advanced behavioral animation in virtual humans, which addresses the challenging open problem of simulating social interactions between pedestrians in...
Successful interaction between autonomous agents is contingent on those agents making decisions consistent with the expectations of their peers -- these expectations are based on ...