OpenDP a free Reinforcement Learning toolbox for discrete time control problems

Sylvain Gelly, Olivier TeytaudSPIRE 2006

Abstract

OpenDP (http://opendp.sourceforge.net) is a free software (under GPL) written in C++ for control problems: (i) with discrete time steps (either finite horizon, or approximation of infinite horizon by temporal-ring for stationnary problems), (ii) where the transition function newState = T (state, decision) can be encoded in C++, (iii) possibly stochastic (with the function T above depending on some random process).
BibTeX
@inproceedings{gelly2006opendp,
  author = {Sylvain Gelly and Olivier Teytaud},
  title = {{OpenDP a free Reinforcement Learning toolbox for discrete time control problems}},
  booktitle = {SPIRE},
  year = {2006},
}

Loading related content...

Figure