Hanabi cooperative imperfect-information learning challenge

What changed

Organizes self-play and ad-hoc teamwork challenges for cooperative imperfect-information Hanabi, specifying an environment interface and sample-limited versus unlimited learning protocols.

Scientific scope

Organizes self-play and ad-hoc teamwork challenges for cooperative imperfect-information Hanabi, specifying an environment interface and sample-limited versus unlimited learning protocols. The record concerns the 2019 challenge and its stated protocols. Later living-document features are not backdated. Default observations retain information derived from hints, so the challenge is not automatically a test of memory alone.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. The record concerns the 2019 challenge and its stated protocols. Later living-document features are not backdated. Default observations retain information derived from hints, so the challenge is not automatically a test of memory alone.

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.

• The Hanabi Challenge: A New Frontier for AI Research

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