AWhat changed
Reframed imperfect-information learning/search around public belief states, training value/policy functions using self-play subgame solving rather than treating hidden-world states as ordinary perfect-information leaves.
Scientific scope
Reframed imperfect-information learning/search around public belief states, training value/policy functions using self-play subgame solving rather than treating hidden-world states as ordinary perfect-information leaves. Originalv1 convergence statement is tabular/idealized and two-player zero-sum; bounded-accuracy subgame solving and exploration assumptions matter. Practical neural approximation and finite poker experiments do not prove a general deep-learning Nash guarantee. Common-knowledge rules/algorithms and legal belief construction are assumed; predecessor belief-state/decomposition ideas are credited.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Originalv1 convergence statement is tabular/idealized and two-player zero-sum; bounded-accuracy subgame solving and exploration assumptions matter. Practical neural approximation and finite poker experiments do not prove a general deep-learning Nash guarantee. Common-knowledge rules/algorithms and legal belief construction are assumed; predecessor belief-state/decomposition ideas are credited.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
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