AWhat changed
Trained a causal Transformer on interleaved return-to-go, state and action histories to predict actions by supervised learning, conditioning generation on desired returns at inference.
Scientific scope
Trained a causal Transformer on interleaved return-to-go, state and action histories to predict actions by supervised learning, conditioning generation on desired returns at inference. Default training predicts actions rather than fitting all trajectory variables. A desired return need not be attainable or supported by the offline data. Original v1 includes Michael Laskin; first two authors contributed equally and final two advised equally. Does not certify optimal actions for arbitrary environments.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Default training predicts actions rather than fitting all trajectory variables. A desired return need not be attainable or supported by the offline data. Original v1 includes Michael Laskin; first two authors contributed equally and final two advised equally. Does not certify optimal actions for arbitrary environments.
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