Distributed power control is an important issue in wireless networks. Recently, noncooperative game theory has been applied to investigate interesting solutions to this problem. Th...
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...
We describe a simple environment to study cooperation between two agents and a method of achieving cooperation in that environment. The environment consists of randomly generated ...
— 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...