{"id":"https://openalex.org/keywords/deterministic-policy-gradient","display_name":"deterministic policy gradient","description":"A reinforcement-learning method that optimizes a deterministic action-selection policy by following gradients of expected reward.","display_name_alternatives":["deterministic policy gradients","deterministic policy gradient method","deterministic policy gradient algorithm","DPG"],"ids":{"openalex":"https://openalex.org/keywords/deterministic-policy-gradient","wikidata":null},"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.516,"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":0.516,"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":0.0721,"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":263,"cited_by_count":28278,"works_api_url":"https://api.openalex.org/works?filter=keywords.id:keywords/deterministic-policy-gradient","updated_date":"2026-11-19T04:05:57","created_date":"2026-09-30T00:00:00"}
