{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/divide-and-conquer-reinforcement-learning","title":"Divide-and-Conquer Reinforcement Learning","arxiv_id":"1711.09874","date":"2017-11-27","proceeding":"ICLR 2018 1","authors":["Dibya Ghosh","Avi Singh","Aravind Rajeswaran","Vikash Kumar","Sergey Levine"],"abstract":"Standard model-free deep reinforcement learning (RL) algorithms sample a new\ninitial state for each trial, allowing them to optimize policies that can\nperform well even in highly stochastic environments. However, problems that\nexhibit considerable initial state variation typically produce high-variance\ngradient estimates for model-free RL, making direct policy or value function\noptimization challenging. In this paper, we develop a novel algorithm that\ninstead partitions the initial state space into \"slices\", and optimizes an\nensemble of policies, each on a different slice. The ensemble is gradually\nunified into a single policy that can succeed on the whole state space. This\napproach, which we term divide-and-conquer RL, is able to solve complex tasks\nwhere conventional deep RL methods are ineffective. Our results show that\ndivide-and-conquer RL greatly outperforms conventional policy gradient methods\non challenging grasping, manipulation, and locomotion tasks, and exceeds the\nperformance of a variety of prior methods. Videos of policies learned by our\nalgorithm can be viewed at http://bit.ly/dnc-rl","url_abs":"http://arxiv.org/abs/1711.09874v2","url_pdf":"http://arxiv.org/pdf/1711.09874v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"divide-and-conquer-reinforcement-learning","repo_url":"https://github.com/dibyaghosh/dnc","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"policy-gradient-methods","task_name":"Policy Gradient Methods"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.09874","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}