User menu

QL2, a simple reinforcement learning scheme for two-player zero-sum Markov games

Bibliographic reference Frénay, Benoît ; Saerens, Marco. QL2, a simple reinforcement learning scheme for two-player zero-sum Markov games.18th European Symposium on Artificial Neural Networks (Brugge(Belgium), Apr, 2008). In: Proceedings of the 16th European Symposium on Artificial Neural Networks, 2009
Permanent URL http://hdl.handle.net/2078.1/58983