{"id":"https://openalex.org/keywords/double-q-learning","display_name":"double Q-learning","description":"A reinforcement learning algorithm that reduces value overestimation by using separate estimates for action selection and action evaluation.","display_name_alternatives":["double Q-learning algorithm"],"ids":{"openalex":"https://openalex.org/keywords/double-q-learning","wikidata":null},"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.3201,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.3201,"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":462,"cited_by_count":33709,"works_api_url":"https://api.openalex.org/works?filter=keywords.id:keywords/double-q-learning","updated_date":"2026-11-17T04:05:58","created_date":"2026-09-30T00:00:00"}
