Parallelizing Counterfactual Regret Minimization

• URL: http://arxiv.org/abs/2605.14277v1
• Date: Thu, 14 May 2026 02:22:27 GMT
• Title: Parallelizing Counterfactual Regret Minimization
• Abstract summary: We parallelize the family of counterfactual regret minimization (CFR) algorithms.<n>We show that our CFR implementation on a GPU is up to four orders of magnitude faster than Google DeepMind OpenSpiel's CFR implementations on a CPU.
• Score: 62.94836578759359
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Parallelization has played an instrumental role in the field of artificial intelligence (AI), drastically reducing the time taken to train and evaluate large AI models. In contrast to its impact in the broader field of AI, applying parallelization to computational game solving is relatively unexplored, despite its great potential. In this paper, we parallelize the family of counterfactual regret minimization (CFR) algorithms, which were central to important breakthroughs for solving large imperfect-information games. We present a generalized parallelization framework, reframing CFR as a series of linear algebra operations. Then, existing techniques for parallelizing linear algebra operations can be applied to accelerate CFR. We also describe how our technique can be applied to other tabular members of the CFR family of algorithms, including the state-of-the-art, such as CFR+, discounted CFR, and predictive variants of CFR. Experimentally, we show that our CFR implementation on a GPU is up to four orders of magnitude faster than Google DeepMind OpenSpiel's CFR implementations on a CPU.

Related papers

• Deep (Predictive) Discounted Counterfactual Regret Minimization [47.323787598768284]
  We propose an efficient model-free neural CFR algorithm, overcoming the limitations of existing methods in approximating advanced CFR variants.<n> Experimental results show that, compared with model-free neural algorithms, it exhibits faster convergence in typical imperfect-information games.
  arXiv  Detail & Related papers  (2025-11-11T12:38:08Z)
• Accelerating Nash Equilibrium Convergence in Monte Carlo Settings Through Counterfactual Value Based Fictitious Play [0.0]
  We introduce a new MC-based algorithm for solving imperfect information games, called MCCFVFP. MCCFVFP combines CFR's counterfactual value calculations with fictitious play's best response strategy. Results show that MCCFVFP achieved convergence speeds approximately 20%$sim$50% faster than the most advanced MCCFR variants.
  arXiv  Detail & Related papers  (2023-09-04T09:16:49Z)
• Hierarchical Deep Counterfactual Regret Minimization [53.86223883060367]
  In this paper, we introduce the first hierarchical version of Deep CFR, an innovative method that boosts learning efficiency in tasks involving extensively large state spaces and deep game trees. A notable advantage of HDCFR over previous works is its ability to facilitate learning with predefined (human) expertise and foster the acquisition of skills that can be transferred to similar tasks.
  arXiv  Detail & Related papers  (2023-05-27T02:05:41Z)
• Large-scale Optimization of Partial AUC in a Range of False Positive Rates [51.12047280149546]
  The area under the ROC curve (AUC) is one of the most widely used performance measures for classification models in machine learning. We develop an efficient approximated gradient descent method based on recent practical envelope smoothing technique. Our proposed algorithm can also be used to minimize the sum of some ranked range loss, which also lacks efficient solvers.
  arXiv  Detail & Related papers  (2022-03-03T03:46:18Z)
• Equivalence Analysis between Counterfactual Regret Minimization and Online Mirror Descent [67.60077332154853]
  Counterfactual Regret Minimization (CFR) is a regret minimization algorithm that minimizes the total regret by minimizing the local counterfactual regrets. Follow-the-Regularized-Lead (FTRL) and Online Mirror Descent (OMD) algorithms are regret minimization algorithms in Online Convex Optimization. We provide a new way to analyze and extend CFRs, by proving that CFR with Regret Matching and CFR with Regret Matching+ are special forms of FTRL and OMD.
  arXiv  Detail & Related papers  (2021-10-11T02:12:25Z)
• Model-free Neural Counterfactual Regret Minimization with Bootstrap Learning [10.816436463322237]
  Current CFR algorithms have to approximate the cumulative regrets with neural networks. A new CFR variant, Recursive CFR, is proposed, in which the cumulative regrets are recovered by Recursive Substitute Values (RSVs) It is proved the new Recursive CFR converges to a Nash equilibrium. Experimental results show that the new algorithm can match the state-of-the-art neural CFR algorithms but with less training overhead.
  arXiv  Detail & Related papers  (2020-12-03T12:26:50Z)
• Sparsified Linear Programming for Zero-Sum Equilibrium Finding [89.30539368124025]
  We present a totally different approach to the problem, which is competitive and often orders of magnitude better than the prior state of the art. With experiments on poker endgames, we demonstrate, for the first time, that modern linear program solvers are competitive against even game-specific modern variants of CFR.
  arXiv  Detail & Related papers  (2020-06-05T13:48:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.