{"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/near-optimal-representation-learning-for","title":"Near-Optimal Representation Learning for Hierarchical Reinforcement Learning","arxiv_id":"1810.01257","date":"2018-10-02","proceeding":"ICLR 2019 5","authors":["Ofir Nachum","Shixiang Gu","Honglak Lee","Sergey Levine"],"abstract":"We study the problem of representation learning in goal-conditioned\nhierarchical reinforcement learning. In such hierarchical structures, a\nhigher-level controller solves tasks by iteratively communicating goals which a\nlower-level policy is trained to reach. Accordingly, the choice of\nrepresentation -- the mapping of observation space to goal space -- is crucial.\nTo study this problem, we develop a notion of sub-optimality of a\nrepresentation, defined in terms of expected reward of the optimal hierarchical\npolicy using this representation. We derive expressions which bound the\nsub-optimality and show how these expressions can be translated to\nrepresentation learning objectives which may be optimized in practice. Results\non a number of difficult continuous-control tasks show that our approach to\nrepresentation learning yields qualitatively better representations as well as\nquantitatively better hierarchical policies, compared to existing methods (see\nvideos at https://sites.google.com/view/representation-hrl).","url_abs":"http://arxiv.org/abs/1810.01257v2","url_pdf":"http://arxiv.org/pdf/1810.01257v2.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":"near-optimal-representation-learning-for","repo_url":"https://github.com/tensorflow/models","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"near-optimal-representation-learning-for","repo_url":"https://github.com/AlexZhaoZt/Temporal_Leap_HRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"near-optimal-representation-learning-for","repo_url":"https://github.com/brandontrabucco/efficient-hrl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"near-optimal-representation-learning-for","repo_url":"https://github.com/hebowei2000/deep-reinforcement-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"near-optimal-representation-learning-for","repo_url":"https://github.com/sumkumar/hiro_impl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"near-optimal-representation-learning-for","repo_url":"https://github.com/tensorflow/models/tree/master/research/efficient-hrl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"2d-human-pose-estimation","task_name":"2D Human Pose Estimation"},{"task_slug":"continuous-control","task_name":"Continuous Control"},{"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":"representation-learning","task_name":"Representation Learning"},{"task_slug":"continuous-control","task_name":"continuous-control"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.01257","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}