{"id":"https://openalex.org/keywords/reward-models","display_name":"reward models","description":"Machine-learning models that assign scores to outputs according to human preferences or other specified reward criteria.","display_name_alternatives":["reward model"],"ids":{"openalex":"https://openalex.org/keywords/reward-models","wikidata":null},"primary_topic":null,"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.1655,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0874,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.0855,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"works_count":961,"cited_by_count":20661,"works_api_url":"https://api.openalex.org/works?filter=keywords.id:keywords/reward-models","updated_date":"2026-11-22T04:06:09","created_date":"2026-09-30T00:00:00"}
