A reinforcement learning method for maximizing undiscounted rewards. Schwartz, A. In Proc. Int. Conf. Mach. Learn., volume 298, pages 298–305, 1993.
bibtex   
@InProceedings{SCC.Schwartz1993,
  author    = {Schwartz, Anton},
  title     = {A reinforcement learning method for maximizing undiscounted rewards},
  booktitle = {Proc. Int. Conf. Mach. Learn.},
  year      = {1993},
  volume    = {298},
  pages     = {298--305},
  owner     = {rkamalapurkar},
  timestamp = {2016.05.18},
}

Downloads: 0