On-Line Policy Gradient Estimation with Multi-Step Sampling

Yan-Jie Li, Fang Cao, Xi-Ren Cao. On-Line Policy Gradient Estimation with Multi-Step Sampling. Discrete Event Dynamic Systems, 20(1):3-17, 2010. [doi]

@article{LiCC10,
  title = {On-Line Policy Gradient Estimation with Multi-Step Sampling},
  author = {Yan-Jie Li and Fang Cao and Xi-Ren Cao},
  year = {2010},
  doi = {10.1007/s10626-009-0078-3},
  url = {http://dx.doi.org/10.1007/s10626-009-0078-3},
  researchr = {https://researchr.org/publication/LiCC10},
  cites = {0},
  citedby = {0},
  journal = {Discrete Event Dynamic Systems},
  volume = {20},
  number = {1},
  pages = {3-17},
}