{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/stable-predictive-optimistic-counterfactual","title":"Stable-Predictive Optimistic Counterfactual Regret Minimization","arxiv_id":"1902.04982","date":"2019-02-13","proceeding":null,"authors":["Gabriele Farina","Christian Kroer","Noam Brown","Tuomas Sandholm"],"abstract":"The CFR framework has been a powerful tool for solving large-scale\nextensive-form games in practice. However, the theoretical rate at which past\nCFR-based algorithms converge to the Nash equilibrium is on the order of\n$O(T^{-1/2})$, where $T$ is the number of iterations. In contrast, first-order\nmethods can be used to achieve a $O(T^{-1})$ dependence on iterations, yet\nthese methods have been less successful in practice. In this work we present\nthe first CFR variant that breaks the square-root dependence on iterations. By\ncombining and extending recent advances on predictive and stable regret\nminimizers for the matrix-game setting we show that it is possible to leverage\n\"optimistic\" regret minimizers to achieve a $O(T^{-3/4})$ convergence rate\nwithin CFR. This is achieved by introducing a new notion of\nstable-predictivity, and by setting the stability of each counterfactual regret\nminimizer relative to its location in the decision tree. Experiments show that\nthis method is faster than the original CFR algorithm, although not as fast as\nnewer variants, in spite of their worst-case $O(T^{-1/2})$ dependence on\niterations.","url_abs":"http://arxiv.org/abs/1902.04982v1","url_pdf":"http://arxiv.org/pdf/1902.04982v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"stable-predictive-optimistic-counterfactual","repo_url":"https://github.com/gabrfarina/exp-a-spiel","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":null,"task_name":"counterfactual"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.04982","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}