Efficient Learning in Games - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2006

Efficient Learning in Games

Raghav Aras
  • Function : Author
  • PersonId : 830439
Alain Dutech


We consider the problem of learning strategy selection in games. The theoretical solution to this problem is a distribution over strategies that responds to a Nash equilibrium of the game. When the payoff function of the game is not known to the participants, such a distribution must be approximated directly through repeated play. Full knowledge of the payoff function, on the other hand, restricts agents to be strictly rational. In this classical approach, agents are bound to a Nash equilibrium, even when a globally better solution is obtainable. In this paper, we present an algorithm that allows agents to capitalize on their very lack of information about the payoff structure. The principle we propose is that agents resort to the manipulation of their own payoffs, during the course of learning, to find a ``game'' that gives them a higher payoff than when no manipulation occurs. In essence, the payoffs are considered an extension of the strategy set. At all times, agents remain rational vis-à-vis the information available. In self-play, the algorithm affords a globally efficient payoff (if it exists).
Fichier principal
Vignette du fichier
aras_EfficientLearnGame_CAP06.pdf (76.3 Ko) Télécharger le fichier

Dates and versions

inria-00102188 , version 1 (29-09-2006)


  • HAL Id : inria-00102188 , version 1


Raghav Aras, Alain Dutech, François Charpillet. Efficient Learning in Games. Conférence Francophone sur l'Apprentissage Automatique - CAP 2006, 2006, Trégastel, France. ⟨inria-00102188⟩
164 View
173 Download


Gmail Facebook Twitter LinkedIn More