Training a deep policy gradient-based neural network with asynchronous learners on a simulated robotic problem

Winfried Lötzsch, Julien Vitay, Fred H. Hamker. Training a deep policy gradient-based neural network with asynchronous learners on a simulated robotic problem. In Maximilian Eibl, Martin Gaedke, editors, 47. Jahrestagung der Gesellschaft für Informatik, Informatik 2017, Chemnitz, Germany, September 25-29, 2017. Volume P-275 of LNI, pages 2143-2154, GI, 2017. [doi]

@inproceedings{LotzschVH17,
  title = {Training a deep policy gradient-based neural network with asynchronous learners on a simulated robotic problem},
  author = {Winfried Lötzsch and Julien Vitay and Fred H. Hamker},
  year = {2017},
  doi = {10.18420/in2017_214},
  url = {https://doi.org/10.18420/in2017_214},
  researchr = {https://researchr.org/publication/LotzschVH17},
  cites = {0},
  citedby = {0},
  pages = {2143-2154},
  booktitle = {47. Jahrestagung der Gesellschaft für Informatik, Informatik 2017, Chemnitz, Germany, September 25-29, 2017},
  editor = {Maximilian Eibl and Martin Gaedke},
  volume = {P-275},
  series = {LNI},
  publisher = {GI},
  isbn = {978-3-88579-669-5},
}