Eric Piette

Assistant Lecturer (ATER) at the Centre de Recherche en Informatique de Lens (CRIL), I just completed my thesis entitled "A Stochastic Constraint-Based Approach to General Game Playing" supervised by Frédéric Koriche, Sylvain Lagrue and Sébastien Tabary.

My PhD focuses on General Game Playing (GGP) whose the primary objective is to create an artificial intelligence which is able to play strategically at a variety of games. Thanks to my work, we introduced a new kind of approach based on the stochastic constraint satisfaction problem (SCSP) and on the Bandit-based stochastic sampling. Moreover, I realised a general game player called WoodStock using our approach which won the International General Game Playing Competition 2016 (IGGPC'16).

More information about my thesis here.

Keywords : General Game Playing, machine learning, knownledge representation, constraint programming.



L’Intelligence Artificielle se définit comme le contraire de la bêtise naturelle.

Woody Allen