{"id":"https://openalex.org/keywords/q-function-estimation","display_name":"Q-function estimation","description":"Estimation of the action-value function, which predicts expected cumulative reward for state-action choices in reinforcement learning and policy evaluation.","display_name_alternatives":["estimation of the action-value function"],"ids":{"openalex":"https://openalex.org/keywords/q-function-estimation","wikidata":null},"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6622,"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":0.6622,"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":0.0986,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"works_count":107,"cited_by_count":2037,"works_api_url":"https://api.openalex.org/works?filter=keywords.id:keywords/q-function-estimation","updated_date":"2026-11-22T04:06:09","created_date":"2026-09-30T00:00:00"}
