{"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/hierarchical-deep-reinforcement-learning","title":"Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation","arxiv_id":"1604.06057","date":"2016-04-20","proceeding":"NeurIPS 2016 12","authors":["Tejas D. Kulkarni","Karthik R. Narasimhan","Ardavan Saeedi","Joshua B. Tenenbaum"],"abstract":"Learning goal-directed behavior in environments with sparse feedback is a\nmajor challenge for reinforcement learning algorithms. The primary difficulty\narises due to insufficient exploration, resulting in an agent being unable to\nlearn robust value functions. Intrinsically motivated agents can explore new\nbehavior for its own sake rather than to directly solve problems. Such\nintrinsic behaviors could eventually help the agent solve tasks posed by the\nenvironment. We present hierarchical-DQN (h-DQN), a framework to integrate\nhierarchical value functions, operating at different temporal scales, with\nintrinsically motivated deep reinforcement learning. A top-level value function\nlearns a policy over intrinsic goals, and a lower-level function learns a\npolicy over atomic actions to satisfy the given goals. h-DQN allows for\nflexible goal specifications, such as functions over entities and relations.\nThis provides an efficient space for exploration in complicated environments.\nWe demonstrate the strength of our approach on two problems with very sparse,\ndelayed feedback: (1) a complex discrete stochastic decision process, and (2)\nthe classic ATARI game `Montezuma's Revenge'.","url_abs":"http://arxiv.org/abs/1604.06057v2","url_pdf":"http://arxiv.org/pdf/1604.06057v2.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":"hierarchical-deep-reinforcement-learning","repo_url":"https://github.com/madeleinesnyder/Subbat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"hierarchical-deep-reinforcement-learning","repo_url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"hierarchical-deep-reinforcement-learning","repo_url":"https://github.com/nishantgurunath/HRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"hierarchical-deep-reinforcement-learning","repo_url":"https://github.com/transedward/pytorch-hdqn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"montezumas-revenge","task_name":"Montezuma's Revenge"},{"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=1604.06057","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}