mlsanityData to 7 Oct 2026

Revisiting CFR+ and Alternating Updates

arXiv 1810.11542 ↗First posted 26 Oct 2018cs.GTcited by 19

Not on the map. Why?

Abstract (arXiv)

The CFR+ algorithm for solving imperfect information games is a variant of the popular CFR algorithm, with faster empirical performance on a range of problems. It was introduced with a theoretical upper bound on solution error, but subsequent work showed an error in one step of the proof. We provide updated proofs to recover the original bound.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 5; 2023: 4; 2024: 2; 2025: 1; 2026: 3.

19 papers.

Sort:

  1. 2021Last-iterate Convergence in Extensive-Form Gamescited by 27
  2. 2022Near-Optimal Learning of Extensive-Form Games with Imperfect Informationcited by 26
  3. 2024A Survey on Self-play Methods in Reinforcement Learningcited by 26
  4. 2021Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recallcited by 21
  5. 2022Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descentcited by 15
  6. 2023Regret Matching+: (In)Stability and Fast Convergence in Gamescited by 13
  7. 2022Adapting to game trees in zero-sum imperfect information gamescited by 11
  8. 2022HSVI can solve zero-sum Partially Observable Stochastic Gamescited by 8
  9. 2023Last-Iterate Convergence Properties of Regret-Matching Algorithms in Gamescited by 5
  10. 2021Conic Blackwell Algorithm: Parameter-Free Convex-Concave Saddle-Point Solvingcited by 4
  11. 2022Solving optimization problems with Blackwell approachabilitycited by 4
  12. 2023Local and adaptive mirror descents in extensive-form gamescited by 2
7 more
  1. 2021Revisiting Game Representations: The Hidden Costs of Efficiency in Sequential Decision-making Algorithmscited by 0
  2. 2023A Generalized Extensive-Form Fictitious Play Algorithmcited by 0
  3. 2024GPU-Accelerated Counterfactual Regret Minimizationcited by 0
  4. 2025Efficient Last-Iterate Convergence in Regret Minimization via Adaptive Reward Transformationcited by 0
  5. 2026CFR without Unbiasedness: Deterministic Guarantees for Persistent Public-Chance Schedulescited by 0
  6. 2026Minimax Alternating Regret for the Experts Problem and Online Convex Optimizationcited by 0
  7. 2026GPU-CFR: 80x Faster Counterfactual Regret Minimization by Compiling the Game to Static Dataflow and CUDA Graph Replaycited by 0