Recently, a small number of papers have appeared in which the authors implement stochastic search algorithms, such as evolutionary computation, to generate game content, such as le...
Julian Togelius, Georgios N. Yannakakis, Kenneth O...
We consider the problem of learning to attain multiple goals in a dynamic environment, which is initially unknown. In addition, the environment may contain arbitrarily varying ele...
— In the real world, noisy sensors and limited communication make it difficult for robot teams to coordinate in tightly coupled tasks. Team members cannot simply apply single-ro...
Rosemary Emery-Montemerlo, Geoffrey J. Gordon, Jef...
R-max is a very simple model-based reinforcement learning algorithm which can attain near-optimal average reward in polynomial time. In R-max, the agent always maintains a complet...
We introduce a game setting called a joint process, where the history of actions determine the state, and the state and agent properties determine the payoff. This setting is a sp...