no code implementations • NeurIPS 2014 • Balázs Szörényi, Gunnar Kedenburg, Remi Munos
We consider the problem of online planning in a Markov decision process with discounted rewards for any given initial state.
no code implementations • NeurIPS 2013 • Gunnar Kedenburg, Raphael Fonteneau, Remi Munos
This paper addresses the problem of online planning in Markov Decision Processes using only a generative model.