Regularized Policy Gradients: Direct Variance Reduction in Policy Gradient Estimation

Tingting Zhao, Gang Niu, Ning Xie 0003, Jucheng Yang, Masashi Sugiyama. Regularized Policy Gradients: Direct Variance Reduction in Policy Gradient Estimation. In Proceedings of The 7th Asian Conference on Machine Learning, ACML 2015, Hong Kong, November 20-22, 2015. Volume 45 of JMLR Workshop and Conference Proceedings, pages 333-348, JMLR.org, 2015. [doi]

@inproceedings{ZhaoNXYS15,
  title = {Regularized Policy Gradients: Direct Variance Reduction in Policy Gradient Estimation},
  author = {Tingting Zhao and Gang Niu and Ning Xie 0003 and Jucheng Yang and Masashi Sugiyama},
  year = {2015},
  url = {http://jmlr.org/proceedings/papers/v45/Zhao15b.html},
  researchr = {https://researchr.org/publication/ZhaoNXYS15},
  cites = {0},
  citedby = {0},
  pages = {333-348},
  booktitle = {Proceedings of The 7th Asian Conference on Machine Learning, ACML 2015, Hong Kong, November 20-22, 2015},
  volume = {45},
  series = {JMLR Workshop and Conference Proceedings},
  publisher = {JMLR.org},
}