AWhat changed
Learned action-relevant features through inverse dynamics and used forward prediction error in that feature space as an intrinsic exploration reward.
Scientific scope
Learned action-relevant features through inverse dynamics and used forward prediction error in that feature space as an intrinsic exploration reward. Inherits prediction-error curiosity and inverse dynamics; the contribution is their feature-learning combination. Encouraging controllability-sensitive features is not a proof of ignoring all uncontrollable noise or solving every sparse-reward problem; game and simulated-control results are task-dependent.
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 prediction-error curiosity and inverse dynamics; the contribution is their feature-learning combination. Encouraging controllability-sensitive features is not a proof of ignoring all uncontrollable noise or solving every sparse-reward problem; game and simulated-control results are task-dependent.
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