AWhat changed
Combined actor-critic experience replay with truncated importance weighting and bias correction, Retrace-based value targets and a computationally efficient trust-region update.
Scientific scope
Combined actor-critic experience replay with truncated importance weighting and bias correction, Retrace-based value targets and a computationally efficient trust-region update. Inherits A3C, Retrace and trust-region/importance-sampling methods. Bias-correction identities do not certify arbitrary neural training as globally unbiased or convergent.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Inherits A3C, Retrace and trust-region/importance-sampling methods. Bias-correction identities do not certify arbitrary neural training as globally unbiased or convergent.
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