{"id":"https://openalex.org/keywords/policy-gradient","display_name":"policy gradient","description":"Policy gradient is a family of reinforcement learning methods that optimize a policy by estimating gradients of expected reward with respect to its parameters.","display_name_alternatives":["policy gradient method","policy gradients","policy gradient algorithm","policy gradient algorithms","policy gradient methods"],"ids":{"openalex":"https://openalex.org/keywords/policy-gradient","wikidata":"https://www.wikidata.org/wiki/Q113840014"},"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4796,"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":0.4796,"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":3734,"cited_by_count":74940,"works_api_url":"https://api.openalex.org/works?filter=keywords.id:keywords/policy-gradient","updated_date":"2026-10-21T04:06:17","created_date":"2026-09-30T00:00:00"}