{"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/feudal-networks-for-hierarchical","title":"FeUdal Networks for Hierarchical Reinforcement Learning","arxiv_id":"1703.01161","date":"2017-03-03","proceeding":"ICML 2017 8","authors":["Alexander Sasha Vezhnevets","Simon Osindero","Tom Schaul","Nicolas Heess","Max Jaderberg","David Silver","Koray Kavukcuoglu"],"abstract":"We introduce FeUdal Networks (FuNs): a novel architecture for hierarchical\nreinforcement learning. Our approach is inspired by the feudal reinforcement\nlearning proposal of Dayan and Hinton, and gains power and efficacy by\ndecoupling end-to-end learning across multiple levels -- allowing it to utilise\ndifferent resolutions of time. Our framework employs a Manager module and a\nWorker module. The Manager operates at a lower temporal resolution and sets\nabstract goals which are conveyed to and enacted by the Worker. The Worker\ngenerates primitive actions at every tick of the environment. The decoupled\nstructure of FuN conveys several benefits -- in addition to facilitating very\nlong timescale credit assignment it also encourages the emergence of\nsub-policies associated with different goals set by the Manager. These\nproperties allow FuN to dramatically outperform a strong baseline agent on\ntasks that involve long-term credit assignment or memorisation. We demonstrate\nthe performance of our proposed system on a range of tasks from the ATARI suite\nand also from a 3D DeepMind Lab environment.","url_abs":"http://arxiv.org/abs/1703.01161v2","url_pdf":"http://arxiv.org/pdf/1703.01161v2.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":"feudal-networks-for-hierarchical","repo_url":"https://github.com/4rChon/NL-FuN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"hierarchical-reinforcement-learning","task_name":"Hierarchical Reinforcement Learning"},{"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=1703.01161","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}