A C++ Template-Based Reinforcement Learning Library: Fitting the Code to the Mathematics

Hervé Frezza-Buet (1) , Matthieu Geist (1)

1 IMS : Information, Multimodalité & Signal

This paper introduces the rllib as an original C++ template-based library oriented toward value function estimation. Generic programming is promoted here as a way of having a good t between the mathematics of reinforcement learning and their implementation in a library. Main concepts of rllib are presented, as well as a short example.

Mots clés: reinforcement learning; C++; generic programming

Domaines: Apprentissage [cs.LG]

Hervé Frezza-Buet, Matthieu Geist. A C++ Template-Based Reinforcement Learning Library: Fitting the Code to the Mathematics. Journal of Machine Learning Research, 2013, 14 (1), pp.625-628. ⟨hal-00914768⟩