@article{approximateexploitabilitylearningabest,
  title = {Approximate exploitability: Learning a best response in large games},
  author = {Finbarr Timbers and Nolan Bard and Edward Lockhart and Marc Lanctot and Martin Schmid and Neil Burch and Julian Schrittwieser and Thomas Hubert and Michael Bowling},
  year = {2020},
  eprint = {2004.09677},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2004.09677v5},
}