{"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/training-agents-using-upside-down","title":"Training Agents using Upside-Down Reinforcement Learning","arxiv_id":"1912.02877","date":"2019-12-05","proceeding":null,"authors":["Rupesh Kumar Srivastava","Pranav Shyam","Filipe Mutz","Wojciech Jaśkowski","Jürgen Schmidhuber"],"abstract":"We develop Upside-Down Reinforcement Learning (UDRL), a method for learning to act using only supervised learning techniques. Unlike traditional algorithms, UDRL does not use reward prediction or search for an optimal policy. Instead, it trains agents to follow commands such as \"obtain so much total reward in so much time.\" Many of its general principles are outlined in a companion report; the goal of this paper is to develop a practical learning algorithm and show that this conceptually simple perspective on agent training can produce a range of rewarding behaviors for multiple episodic environments. Experiments show that on some tasks UDRL's performance can be surprisingly competitive with, and even exceed that of some traditional baseline algorithms developed over decades of research. Based on these results, we suggest that alternative approaches to expected reward maximization have an important role to play in training useful autonomous agents.","url_abs":"https://arxiv.org/abs/1912.02877v2","url_pdf":"https://arxiv.org/pdf/1912.02877v2.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":"training-agents-using-upside-down","repo_url":"https://github.com/TrentBrick/RewardConditionedUDRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"training-agents-using-upside-down","repo_url":"https://github.com/bprabhakar/upside-down-reinforcement-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"training-agents-using-upside-down","repo_url":"https://github.com/drozzy/upsidedown","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"training-agents-using-upside-down","repo_url":"https://github.com/haron1100/Upside-Down-Reinforcement-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"training-agents-using-upside-down","repo_url":"https://github.com/ken011528/UpsideDown-reinforcement-learning-implement-by-tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"training-agents-using-upside-down","repo_url":"https://github.com/parthchadha/upsideDownRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"training-agents-using-upside-down","repo_url":"https://github.com/BY571/Upside-Down-Reinforcement-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"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":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1912.02877","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}