{"id":"https://openalex.org/keywords/off-policy-learning","display_name":"off-policy learning","description":"A reinforcement learning approach that learns or evaluates a target policy using experience generated by a different behavior policy.","display_name_alternatives":["off-policy reinforcement learning"],"ids":{"openalex":"https://openalex.org/keywords/off-policy-learning","wikidata":null},"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6316,"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":0.6316,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.1361,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"works_count":2077,"cited_by_count":44987,"works_api_url":"https://api.openalex.org/works?filter=keywords.id:keywords/off-policy-learning","updated_date":"2026-10-21T04:06:17","created_date":"2026-09-30T00:00:00"}