Potential-based online policy iteration algorithms for Markov decision processes

Haitao Fang, Xi-Ren Cao. Potential-based online policy iteration algorithms for Markov decision processes. IEEE Trans. Automat. Contr., 49(4):493-505, 2004. [doi]

@article{FangC04-2,
  title = {Potential-based online policy iteration algorithms for Markov decision processes},
  author = {Haitao Fang and Xi-Ren Cao},
  year = {2004},
  doi = {10.1109/TAC.2004.825647},
  url = {http://dx.doi.org/10.1109/TAC.2004.825647},
  researchr = {https://researchr.org/publication/FangC04-2},
  cites = {0},
  citedby = {0},
  journal = {IEEE Trans. Automat. Contr.},
  volume = {49},
  number = {4},
  pages = {493-505},
}