Concurrent Q-learning: Reinforcement learning for dynamic goals and environments

Robert Ollington, Peter Vamplew. Concurrent Q-learning: Reinforcement learning for dynamic goals and environments. Int. J. Intell. Syst., 20(10):1037-1052, 2005. [doi]

@article{OllingtonV05,
  title = {Concurrent Q-learning: Reinforcement learning for dynamic goals and environments},
  author = {Robert Ollington and Peter Vamplew},
  year = {2005},
  doi = {10.1002/int.20105},
  url = {http://dx.doi.org/10.1002/int.20105},
  tags = {Meta-Environment},
  researchr = {https://researchr.org/publication/OllingtonV05},
  cites = {0},
  citedby = {0},
  journal = {Int. J. Intell. Syst.},
  volume = {20},
  number = {10},
  pages = {1037-1052},
}