Publications by Tuomas Sandholm

Conference

AWESOME: A General Multiagent Learning Algorithm that Converges in Self-Play and Learns a Best Response Against Stationary Opponents

2003 • Proceedings, Twentieth International Conference on Machine Learning • 1:83-90
Conitzer V, Sandholm T

Conference

BL-WoLF: A Framework For Loss-Bounded Learnability In Zero-Sum Games

2003 • Proceedings, Twentieth International Conference on Machine Learning • 1:91-98
Conitzer V, Sandholm T

Conference

Complexity of determining nonemptiness of the core

2003 • IJCAI International Joint Conference on Artificial Intelligence • 613-618
Conitzer V, Sandholm T

Conference

Complexity results about Nash equilibria

2003 • IJCAI International Joint Conference on Artificial Intelligence • 765-771
Conitzer V, Sandholm T

Conference

Definition and complexity of some basic metareasoning problems

2003 • IJCAI International Joint Conference on Artificial Intelligence • 1099-1106
Conitzer V, Sandholm T

Conference

Making markets and democracy work: A story of incentives and computing

2003 • IJCAI International Joint Conference on Artificial Intelligence • 1649-1671
Sandholm T

Conference

Proceedings of the International Conference on Autonomous Agents: Foreword

2003 • Proceedings of the Interantional Conference on Autonomous Agents • 2:
Rosenschein JS, Wooldridge M, Sandholm T, Yokoo M

Conference

Reinforcement learning to play an optimal nash equilibrium in team Markov games

2003 • Advances in Neural Information Processing Systems
Wang X, Sandholm T
Displaying 451 - 475 of 580