BibTeX

@inproceedings{ewrl18_belousov,
  author =		 "Belousov, B. and  Peters, J.",
  year =		 "2018",
  title =		 "Mean Squared Advantage Minimization as a Consequence of Entropic Policy Improvement Regularization",
  booktitle =		 "European Workshops on Reinforcement Learning (EWRL)",
  key =			 "policy optimization, entropic proximal mappings, actor-critic algorithms",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/BorisBelousov/ewrl18_belousov.pdf",
  crossref =		 "p11164"
}