{"id":"https://openalex.org/keywords/policy-gradient-estimation","display_name":"policy gradient estimation","description":"The computational estimation of gradients that indicate how changes to a parameterized decision policy affect expected rewards in reinforcement learning.","display_name_alternatives":["estimation of policy gradients","policy gradient estimates","policy gradient estimators"],"ids":{"openalex":"https://openalex.org/keywords/policy-gradient-estimation","wikidata":null},"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7702,"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":0.7702,"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":99,"cited_by_count":1873,"works_api_url":"https://api.openalex.org/works?filter=keywords.id:keywords/policy-gradient-estimation","updated_date":"2026-11-21T04:06:33","created_date":"2026-09-30T00:00:00"}
