Residual Reward Models: Leveraging Prior Knowledge for Efficient Preference-based Reinforcement Learning in Robotics

[2507.00611] Residual Reward Models: Leveraging Prior Knowledge for Efficient Preference-based Reinforcement Learning in Robotics Skip to main content Search Submit Donate Log in Computer Science > Machine Learning arXiv:2507.00611 (cs) [Submitted on 1 Jul 2025 ( v1 ), last revised 27 Aug 2026 (this version, v2)] Title: Residual Reward Models: Leveraging Prior Knowledge for Efficient Preference-based Reinforcement Learning in Robotics Authors: Chenyang Cao , Miguel Rogel-García , Mohamed Nabail , Xueqian Wang , Nicholas Rhinehart View PDF HTML (experimental) Abstract: Preference-based Reinforcement Learning (PbRL) provides a promising alternative to heuristic reward design in complex robotic environments. However, PbRL often suffers from poor sample efficiency, requiring extensive and costly human feedback, which limits its real-world applicability. Prior work has proposed learning a reward model from demonstrations and fine-tuning it using preferences. However, when the model is a neural network, transitioning between different loss functions across training phases often leads to unstable optimization and performance degradation. In this paper, we propose a method to effectively leverage prior knowledge with a Residual Reward Model (RRM). An RRM assumes that the true reward of the environment can be split into a sum of two parts: a prior reward and a learned reward. The prior reward is a term available before training, such as an engineering heuristic ``best guess'', a language-generated reward, or a reward function learned from inverse reinforcement learning, and the learned reward is then trained with preferences as a residual offset. Experimental results in Meta-World and DM-Control show that RRMs substantially improve the sample efficiency of common PbRL methods across various prior reward types. Furthermore, we demonstrate the practical efficacy of our method on a physical Franka Panda robot, accelerating policy learning and achieving high success rates in fewer steps than baselines. Comments: 25 pages, 15 figures Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Robotics (cs.RO) Cite as: arXiv:2507.00611 [cs.LG] (or arXiv:2507.00611v2 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2507.00611 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Chenyang Cao [ view email ] [v1] Tue, 1 Jul 2025 09:43:57 UTC (12,258 KB) [v2] Thu, 27 Aug 2026 00:11:11 UTC (3,076 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.LG < prev | next > new | recent | 2025-07 Change to browse by: cs cs.AI cs.RO References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from (opens in new tab) (opens in new tab) (opens in new tab)

Related documents

• Residual Reward Models: Leveraging Prior Knowledge for Efficient Preference-based Reinforcement Learning in Robotics#677389
• Demonstration-Free Success-Probability Reward Learning for Generalist Robot Policies#1118726
• Geometric Action Model for Robot Policy Learning#285414
• A Preference Analysis of Reinforcer Variation and Choice#448414
• Samples That Matter: Principled Policy Learning for Robotics#354225