HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information

# Efficient Learning in Games

1 MAIA - Autonomous intelligent machine
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : 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).
Keywords :
Document type :
Conference papers
Complete list of metadata

Cited literature [11 references]

https://hal.inria.fr/inria-00102188
Contributor : Alain Dutech Connect in order to contact the contributor
Submitted on : Friday, September 29, 2006 - 1:49:16 PM
Last modification on : Wednesday, February 2, 2022 - 3:51:42 PM
Long-term archiving on: : Tuesday, April 6, 2010 - 1:17:27 AM

### Identifiers

• HAL Id : inria-00102188, version 1

### Citation

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

Record views