{"id":"https://openalex.org/keywords/sarsa","display_name":"SARSA","description":"An on-policy reinforcement learning algorithm that updates action values from the current state, action, reward, next state, and next action.","display_name_alternatives":["state-action-reward-state-action"],"ids":{"openalex":"https://openalex.org/keywords/sarsa","wikidata":"https://www.wikidata.org/wiki/Q7388768"},"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4161,"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":0.4161,"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":946,"cited_by_count":14636,"works_api_url":"https://api.openalex.org/works?filter=keywords.id:keywords/sarsa","updated_date":"2026-11-17T04:05:58","created_date":"2026-09-30T00:00:00"}
