{"id":"https://openalex.org/keywords/value-iteration","display_name":"value iteration","description":"Value iteration is a dynamic programming algorithm that repeatedly updates estimates of state values to find optimal policies in Markov decision processes.","display_name_alternatives":["value iteration algorithm","value function iteration"],"ids":{"openalex":"https://openalex.org/keywords/value-iteration","wikidata":null},"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.2545,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.2545,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2182,"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":2988,"cited_by_count":52436,"works_api_url":"https://api.openalex.org/works?filter=keywords.id:keywords/value-iteration","updated_date":"2026-10-22T04:07:25","created_date":"2026-09-30T00:00:00"}