AWhat changed
Fitted an upper expectile of action values conditional on state, backed it into a Q-function while averaging transition noise, and extracted a policy by advantage-weighted regression.
Scientific scope
Fitted an upper expectile of action values conditional on state, backed it into a Q-function while averaging transition noise, and extracted a policy by advantage-weighted regression. Expectiles over data-supported actions are not return quantiles. Avoiding unseen actions in the training losses does not certify the deployed policy stays in support or improves for every dataset; near-maximal limits and finite nonlinear approximation are separate.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Expectiles over data-supported actions are not return quantiles. Avoiding unseen actions in the training losses does not certify the deployed policy stays in support or improves for every dataset; near-maximal limits and finite nonlinear approximation are separate.
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