A reinforcement learning process in extensive form games

Abstract : 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.
Document type :
Journal articles
Complete list of metadatas

https://hal-pjse.archives-ouvertes.fr/halshs-00754083
Contributor : Caroline Bauer <>
Submitted on : Tuesday, November 20, 2012 - 8:42:35 AM
Last modification on : Thursday, February 7, 2019 - 5:22:47 PM

Links full text

Identifiers

Collections

Citation

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

Share

Metrics

Record views

315