{"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/decoupling-dynamics-and-reward-for-transfer","title":"Decoupling Dynamics and Reward for Transfer Learning","arxiv_id":"1804.10689","date":"2018-04-27","proceeding":null,"authors":["Amy Zhang","Harsh Satija","Joelle Pineau"],"abstract":"Current reinforcement learning (RL) methods can successfully learn single\ntasks but often generalize poorly to modest perturbations in task domain or\ntraining procedure. In this work, we present a decoupled learning strategy for\nRL that creates a shared representation space where knowledge can be robustly\ntransferred. We separate learning the task representation, the forward\ndynamics, the inverse dynamics and the reward function of the domain, and show\nthat this decoupling improves performance within the task, transfers well to\nchanges in dynamics and reward, and can be effectively used for online\nplanning. Empirical results show good performance in both continuous and\ndiscrete RL domains.","url_abs":"http://arxiv.org/abs/1804.10689v2","url_pdf":"http://arxiv.org/pdf/1804.10689v2.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":"decoupling-dynamics-and-reward-for-transfer","repo_url":"https://github.com/facebookresearch/ddr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.10689","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}