AWhat changed
Combines diverse versioned environments under a common reset/step interface and promotes learning curves, sample-complexity reporting and reproducible writeups.
Scientific scope
Combines diverse versioned environments under a common reset/step interface and promotes learning curves, sample-complexity reporting and reproducible writeups. The toolkit deliberately specifies environments, not an agent architecture. It integrates inherited ALE/MuJoCo and other tasks; public scoreboards lack a hidden test distribution and do not certify generalization. This is the2016whitepaper/API, not a current-maintenance or Gymnasium statement.
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 toolkit deliberately specifies environments, not an agent architecture. It integrates inherited ALE/MuJoCo and other tasks; public scoreboards lack a hidden test distribution and do not certify generalization. This is the2016whitepaper/API, not a current-maintenance or Gymnasium statement.
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