AWhat changed
Added squared behavior-cloning regularization to TD3 policy updates, normalized state features and scaled the Q contribution using a stopped-gradient estimate of its magnitude.
Scientific scope
Added squared behavior-cloning regularization to TD3 policy updates, normalized state features and scaled the Q contribution using a stopped-gradient estimate of its magnitude. Uses inherited TD3 rather than inventing a new online actor-critic. Runtime and reward comparisons depend on the tested implementations and datasets. Original analysis explicitly reports inter-seed, within-policy and training-time evaluation variance, not a solved robustness guarantee.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Uses inherited TD3 rather than inventing a new online actor-critic. Runtime and reward comparisons depend on the tested implementations and datasets. Original analysis explicitly reports inter-seed, within-policy and training-time evaluation variance, not a solved robustness guarantee.
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