中文
相关论文

相关论文: Variance Reduction in Monte Carlo Counterfactual R…

200 篇论文

Monte-Carlo counterfactual regret minimization (MCCFR) is the state-of-the-art algorithm for solving sequential games that are too large for full tree traversals. It works by using gradient estimates that can be computed via sampling.…

计算机科学与博弈论 · 计算机科学 2020-02-21 Gabriele Farina , Christian Kroer , Tuomas Sandholm

Extensive-form games (EFGs) are a common model of multi-agent interactions with imperfect information. State-of-the-art algorithms for solving these games typically perform full walks of the game tree that can prove prohibitively slow in…

计算机科学与博弈论 · 计算机科学 2019-07-24 Trevor Davis , Martin Schmid , Michael Bowling

Counterfactual Regret Minimization (CFR) and its variants are widely recognized as effective algorithms for solving extensive-form imperfect information games. Recently, many improvements have been focused on enhancing the convergence speed…

人工智能 · 计算机科学 2024-10-29 Ju Qi , Falin Hei , Ting Feng , Dengbing Yi , Zhemei Fang , Yunfeng Luo

Counterfactual regret minimization (CFR) is a family of algorithms for effectively solving imperfect-information games. To enhance CFR's applicability in large games, researchers use neural networks to approximate its behavior. However,…

机器学习 · 计算机科学 2025-11-12 Hang Xu , Kai Li , Haobo Fu , Qiang Fu , Junliang Xing , Jian Cheng

Monte Carlo Counterfactual Regret Minimization (MCCFR) has emerged as a cornerstone algorithm for solving extensive-form games, but its integration with deep neural networks introduces scale-dependent challenges that manifest differently…

人工智能 · 计算机科学 2026-01-29 Zakaria El Jaafari

We describe and analyze a variance reduction approach for Monte Carlo (MC) sampling that accelerates the estimation of statistics of computationally expensive simulation models using an ensemble of models with lower cost. These lower cost…

统计计算 · 统计学 2021-05-04 Alex A. Gorodetsky , Gianluca Geraci , Mike Eldred , John D. Jakeman

Counterfactual regret minimization (CFR) is a family of iterative algorithms that are the most popular and, in practice, fastest approach to approximately solving large imperfect-information games. In this paper we introduce novel CFR…

计算机科学与博弈论 · 计算机科学 2019-02-22 Noam Brown , Tuomas Sandholm

Counterfactual regret minimization (CFR) is a popular method to deal with decision-making problems of two-player zero-sum games with imperfect information. Unlike existing studies that mostly explore for solving larger scale problems or…

机器学习 · 计算机科学 2020-09-15 Huale Li , Xuan Wang , Fengwei Jia , Yifan Li , Yulin Wu , Jiajia Zhang , Shuhan Qi

Counterfactual Regret Minimization (CFR) and its variants developed based upon Regret Matching (RM) have been considered to be the best method to solve incomplete information extensive form games. In addition to RM and CFR, Fictitious Play…

计算机科学与博弈论 · 计算机科学 2023-11-14 Qi Ju

Imperfect Information Games (IIGs) offer robust models for scenarios where decision-makers face uncertainty or lack complete information. Counterfactual Regret Minimization (CFR) has been one of the most successful family of algorithms for…

机器学习 · 计算机科学 2025-11-12 Jiayu Chen , Zhekai Wang , Vaneet Aggarwal

Counterfactual Regret Minimization (CFR) has achieved many fascinating results in solving large-scale Imperfect Information Games (IIGs). Neural network approximation CFR (neural CFR) is one of the promising techniques that can reduce…

机器学习 · 计算机科学 2022-04-20 Weiming Liu , Bin Li , Julian Togelius

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…

计算机科学与博弈论 · 计算机科学 2012-05-04 Marc Lanctot , Richard Gibson , Neil Burch , Martin Zinkevich , Michael Bowling

The Multilevel Monte Carlo method is an efficient variance reduction technique. It uses a sequence of coarse approximations to reduce the computational cost in uncertainty quantification applications. The method is nowadays often considered…

数值分析 · 数学 2018-06-15 Pieterjan Robbe , Dirk Nuyens , Stefan Vandewalle

We propose a variance reduction framework for variational inference using the Multilevel Monte Carlo (MLMC) method. Our framework is built on reparameterized gradient estimators and "recycles" parameters obtained from past update history in…

机器学习 · 统计学 2021-12-03 Masahiro Fujisawa , Issei Sato

Counterfactual regret minimization (CFR) is the most popular algorithm on solving two-player zero-sum extensive games with imperfect information and achieves state-of-the-art performance in practice. However, the performance of CFR is not…

机器学习 · 计算机科学 2018-12-27 Yichi Zhou , Tongzheng Ren , Jialian Li , Dong Yan , Jun Zhu

A considerable chasm has been looming for decades between theory and practice in zero-sum game solving through first-order methods. Although a convergence rate of $T^{-1}$ has long been established, the most effective paradigm in practice…

计算机科学与博弈论 · 计算机科学 2026-02-18 Brian Hu Zhang , Ioannis Anagnostides , Tuomas Sandholm

Counterfactual Regret Minimization (CFR) is the most popular iterative algorithm for solving zero-sum imperfect-information games. Regret-Based Pruning (RBP) is an improvement that allows poorly-performing actions to be temporarily pruned,…

计算机科学与博弈论 · 计算机科学 2016-09-13 Noam Brown , Tuomas Sandholm

Counterfactual Regret Minimization (CFR)} is the popular method for finding approximate Nash equilibrium in two-player zero-sum games with imperfect information. CFR solves games by travsersing the full game tree iteratively, which limits…

人工智能 · 计算机科学 2022-01-04 Huale Li , Xuan Wang , Zengyue Guo , Jiajia Zhang , Shuhan Qi

In statistics and machine learning, approximation of an intractable integration is often achieved by using the unbiased Monte Carlo estimator, but the variances of the estimation are generally high in many applications. Control variates…

机器学习 · 统计学 2019-10-16 Ruosi Wan , Mingjun Zhong , Haoyi Xiong , Zhanxing Zhu

Online game playing algorithms produce high-quality strategies with a fraction of memory and computation required by their offline alternatives. Continual Resolving (CR) is a recent theoretically sound approach to online game playing that…

计算机科学与博弈论 · 计算机科学 2019-03-11 Michal Sustr , Vojtech Kovarik , Viliam Lisy
‹ 上一页 1 2 3 10 下一页 ›