Optimization Issues in KL-Constrained Approximate Policy Iteration. Lazic, N., Hao, B., Abbasi-Yadkori, Y., Schuurmans, D., & Szepesvári, C. CoRR, 2021.
Optimization Issues in KL-Constrained Approximate Policy Iteration [link]Paper  bibtex   
@article{DBLP:journals/corr/abs-2102-06234,
  author    = {Nevena Lazic and
               Botao Hao and
               Yasin Abbasi{-}Yadkori and
               Dale Schuurmans and
               Csaba Szepesv{\'{a}}ri},
  title     = {Optimization Issues in KL-Constrained Approximate Policy Iteration},
  journal   = {CoRR},
  volume    = {abs/2102.06234},
  year      = {2021},
  url       = {https://arxiv.org/abs/2102.06234},
  archivePrefix = {arXiv},
  eprint    = {2102.06234},
  timestamp = {Thu, 18 Feb 2021 00:00:00 +0100},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2102-06234.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

Downloads: 0