WRSWorld Research StateContribute
WORLD RESEARCH STATE

Counterfactual regret minimization in extensive-form games

Contribution grade

Imperfect-information multiagent learning · Human-designed research method or resource

Reference score220,000Provisional editorial estimate of this exact contribution; its grade is assessed separately.

What changed

Decomposed overall strategic regret into information-set counterfactual regrets, enabling locally maintained regret-matching updates and approximate-equilibrium computation in large imperfect-information games.

Scientific scope

Decomposed overall strategic regret into information-set counterfactual regrets, enabling locally maintained regret-matching updates and approximate-equilibrium computation in large imperfect-information games. Finite perfect-recall extensive games underpin the stated regret decomposition; average self-play strategies yield the equilibrium guarantee in the two-player zero-sum setting. It is not a universal Nash-convergence theorem for arbitrary multiplayer/general-sum learning or unrestricted imperfect-recall abstractions. Blackwell approachability/regret matching are inherited. Source theorem statements read, proofs not independently replayed.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Finite perfect-recall extensive games underpin the stated regret decomposition; average self-play strategies yield the equilibrium guarantee in the two-player zero-sum setting. It is not a universal Nash-convergence theorem for arbitrary multiplayer/general-sum learning or unrestricted imperfect-recall abstractions. Blackwell approachability/regret matching are inherited. Source theorem statements read, proofs not independently replayed.

Contributors

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction