Never Give Up: episodic and lifelong novelty for directed exploration

What changed

Combined episodic nearest-neighbor novelty in learned controllability features with lifelong random-network novelty and conditioned value learning across exploration/exploitation settings.

Scientific scope

Combined episodic nearest-neighbor novelty in learned controllability features with lifelong random-network novelty and conditioned value learning across exploration/exploitation settings. Inherits RND, episodic novelty and universal value conditioning. Does not solve exploration in every environment or prove all uncontrollable variations ignored.

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 RND, episodic novelty and universal value conditioning. Does not solve exploration in every environment or prove all uncontrollable variations ignored.

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.

• Never Give Up: Learning Directed Exploration Strategies

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