With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...
We investigate methods for planning in a Markov Decision Process where the cost function is chosen by an adversary after we fix our policy. As a running example, we consider a rob...
H. Brendan McMahan, Geoffrey J. Gordon, Avrim Blum
Evolution of multi-agent teams has been shown to be an effective method of solving complex problems involving the exploration of an unknown problem space. These autonomous and het...
Joshua Rubini, Robert B. Heckendorn, Terence Soule
Through a defined research process we designed objects that behave and respond in specific ways and are part of a networked system that emphasizes autonomous and flocking behavior...
RoboCup projects can face a lack of progress and continuity. The teams change continuously and knowledge gets lost. The approach used in previous years is no longer valid due to ru...