AWhat changed
Pretrained a deep Q-network on demonstration data using temporal-difference, large-margin action-classification and regularization losses, then mixed preserved demonstrations with self-generated replay during learning.
Scientific scope
Pretrained a deep Q-network on demonstration data using temporal-difference, large-margin action-classification and regularization losses, then mixed preserved demonstrations with self-generated replay during learning. Original v1 uses separate demonstration/agent buffers with a controlled fixed sampling proportion; do not import later prioritized-replay/n-step revisions automatically. Inherits Double DQN and supervised imitation losses. Better initial Atari performance is not a safety certificate for real systems or expert-free learning.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Original v1 uses separate demonstration/agent buffers with a controlled fixed sampling proportion; do not import later prioritized-replay/n-step revisions automatically. Inherits Double DQN and supervised imitation losses. Better initial Atari performance is not a safety certificate for real systems or expert-free learning.
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