Fictitious Play for Mean Field Games: Continuous Time Analysis and Applications

von Perrin, Sarah
Veröffentlicht in NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 16 of 27 (2021)

MULTIAGENT EVALUATION UNDER INCOMPLETE INFORMATION

von Rowland, Mark
Veröffentlicht in NeurIPS (33. : 2019 : Vancouver, British Columbia) 32nd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Volume 16 of 20 (2020)

Scaling Mean Field Games by Online Mirror Descent

von Pérolat, Julien
Veröffentlicht in International Conference on Autonomous Agents and Multiagent Systems (21. : 2022 : Online) International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2022) ; Volume 2 of 3 (2022)

Learning Equilibria in Mean-Field Games: introducing Mean-Field PSRO

von Muller, Paul
Veröffentlicht in International Conference on Autonomous Agents and Multiagent Systems (21. : 2022 : Online) International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2022) ; Volume 2 of 3 (2022)

NEURAL REPLICATOR DYNAMICS: MULTIAGENT LEARNING VIA HEDGING POLICY GRADIENTS

von Hennes, Daniel
Veröffentlicht in AAMAS (19. : 2020 : Online) International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2020) ; Volume 1 of 3 (2021)

LEARNING TO PLAY NO-PRESS DIPLOMACY WITH BEST RESPONSE POLICY ITERATION

von Anthony, Thomas
Veröffentlicht in NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 22 of 27 (2021)

FROM POINCARÉ RECURRENCE TO CONVERGENCE IN IMPERFECT INFORMATION GAMES: FINDING EQUILIBRIUM VIA REGULARIZATION

von PEROLAT, JULIEN
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 11 of 16 (2022)

FAST COMPUTATION OF NASH EQUILIBRIA IN IMPERFECT INFORMATION GAMES

von Munos, Remi
Veröffentlicht in International Conference on Machine Learning (37. : 2020 : Online) 37th International Conference on Machine Learning (ICML 2020) ; Part 10 of 15 (2021)