Imitating play from game trajectories: Temporal difference learning versus preference learning

Thomas Philip Runarsson, Simon M. Lucas. Imitating play from game trajectories: Temporal difference learning versus preference learning. In 2012 IEEE Conference on Computational Intelligence and Games, CIG 2012, Granada, Spain, September 11-14, 2012. pages 79-82, IEEE, 2012. [doi]

@inproceedings{RunarssonL12,
  title = {Imitating play from game trajectories: Temporal difference learning versus preference learning},
  author = {Thomas Philip Runarsson and Simon M. Lucas},
  year = {2012},
  doi = {10.1109/CIG.2012.6374141},
  url = {http://dx.doi.org/10.1109/CIG.2012.6374141},
  researchr = {https://researchr.org/publication/RunarssonL12},
  cites = {0},
  citedby = {0},
  pages = {79-82},
  booktitle = {2012 IEEE Conference on Computational Intelligence and Games, CIG 2012, Granada, Spain, September 11-14, 2012},
  publisher = {IEEE},
  isbn = {978-1-4673-1193-9},
}