Trainieren eines Modells mit Verstärkungslernen zur Förderung von Neuheit und Relevanz

Details

Veröffentlichungs-Nr.

EP4621658

Aktenzeichen

EP25164974

Anmeldetag

20. März 2025

Veröffentlichung

24. September 2025

Rechtsraum

EP

IPC

G06N3/092G06N3/045G06N3/096G06F16/00// G06N3/048G06N3/09

Abstract

A technique uses reinforcement learning to train a plural-objective model that generates target items based on the dual objectives of relevance and novelty. The reinforcement learning expresses each state as a combination of a particular source item (e.g., a query) and a particular target item. The reinforcement learning generates an action that indicates whether the target item is selected as a good match for the source item. The reinforcement learning then generates a reward based on the state and the action. In doing so, the reinforcement learning relies on a novelty-reference model for assessing novelty and a relevance-reference model (e.g., a large language model) for assessing relevance. The reinforcement learning then uses the reward to update parameters of the plural-objective model.

Anmelder

Firma

Microsoft Technology Licensing, LLC

Land

🇺🇸 USA

Fachgebiete