A reinforcement learning process in extensive form games

Jean-François Laslier (1) , Bernard Walliser (2)

1 CECO - Laboratoire d'économétrie de l'École polytechnique
2 CERAS - Centre d'enseignement et de recherche en analyse socio-économique

The CPR ("cumulative proportional reinforcement") learning rule stipulates that an agent chooses a move with a probability proportional to the cumulative payoff she obtained in the past with that move. Previously considered for strategies in normal form games (Laslier, Topol and Walliser, Games and Econ. Behav., 2001), the CPR rule is here adapted for actions in perfect information extensive form games. The paper shows that the action-based CPR process converges with probability one to the (unique) subgame perfect equilibrium.

Mots clés: Learning; Polya process; Reinforcement; Subgame Perfect Equilibrium

Domaines: Economies et finances

Jean-François Laslier, Bernard Walliser. A reinforcement learning process in extensive form games. International Journal of Game Theory, 2005, 33 (2), pp.219-227. ⟨10.1007/s001820400194⟩. ⟨halshs-00754083⟩