No-Regret Learning in Extensive-Form Games with Imperfect Recall

@article{Lanctot2012NoRegretLI,
  title={No-Regret Learning in Extensive-Form Games with Imperfect Recall},
  author={Marc Lanctot and Richard G. Gibson and Neil Burch and Michael H. Bowling},
  journal={CoRR},
  year={2012},
  volume={abs/1205.0622}
}
Counterfactual Regret Minimization (CFR) is an efficient no-regret learning algorithm for decision problems modeled as extensive games. CFR’s regret bounds depend on the requirement of perfect recall: players always remember information that was revealed to them and the order in which it was revealed. In games without perfect recall, however, CFR’s guarantees do not apply. In this paper, we present the first regret bound for CFR when applied to a general class of games with imperfect recall. In… CONTINUE READING
Highly Cited
This paper has 59 citations. REVIEW CITATIONS

Citations

Publications citing this paper.

59 Citations

01020'13'15'17
Citations per Year
Semantic Scholar estimates that this publication has 59 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 14 references

We now use Lemma A to prove Theorems 1 and 2: Theorem 2. If Γ is skew well-formed with respect to Γ̆, then the average regret in Γ̆

  • (Zinkevich et al.,
  • 2008

Behavior strategies, mixed strategies and perfect recall

  • Mamoru Kaneko, J. Jude Kline
  • International Journal of Game Theory,
  • 1995
3 Excerpts

Similar Papers

Loading similar papers…