Value Explicit Pretraining for Learning Transferable Representations

[2312.12339] Value Explicit Pretraining for Learning Transferable Representations Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2312.12339 (cs) [Submitted on 19 Dec 2023 ( v1 ), last revised 30 Apr 2026 (this version, v3)] Title: Value Explicit Pretraining for Learning Transferable Representations Authors: Kiran Lekkala , Henghui Bao , Sumedh A. Sontakke , Erdem Biyik , Laurent Itti View a PDF of the paper titled Value Explicit Pretraining for Learning Transferable Representations, by Kiran Lekkala and 4 other authors View PDF HTML (experimental) Abstract: Understanding visual inputs for a given task amidst varied changes is a key challenge posed by visual reinforcement learning agents. We propose \textit{Value Explicit Pretraining} (VEP), a method that learns generalizable representations for transfer reinforcement learning. VEP enables efficient learning of new tasks that share similar objectives as previously learned tasks, by learning an encoder that trains representations to be invariant to changes in environment dynamics and appearance. To pretrain the encoder with \textit{suboptimal unlabeled demonstration data} (sequence of observations and sparse reward signals), we use a self-supervised contrastive loss that enables the model to relate states across different tasks based on the Monte Carlo value estimate that is reflective of task progress, resulting in temporally smooth representations that capture the objective of the task. A major difference between our method and the existing approaches is the use of suboptimal unlabeled data that do not always solve the task. Experiments on Ant locomotion, a realistic navigation simulator and the Atari benchmark show that VEP outperforms current SoTA pretraining methods on the ability to generalize to unseen tasks. VEP achieves up to $2\times$ improvement in rewards, and up to $3\times$ improvement in sample efficiency. For videos of VEP policies, visit our \href{ this https URL }{website}. Comments: Published in Robotics and Automation Letters (RA-L), January 2026 Subjects: Machine Learning (cs.LG) ; Robotics (cs.RO) Cite as: arXiv:2312.12339 [cs.LG] (or arXiv:2312.12339v3 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2312.12339 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Kiran Lekkala [ view email ] [v1] Tue, 19 Dec 2023 17:12:35 UTC (530 KB) [v2] Thu, 7 Mar 2024 10:07:02 UTC (4,822 KB) [v3] Thu, 30 Apr 2026 20:17:03 UTC (1,362 KB) Full-text links: Access Paper: View a PDF of the paper titled Value Explicit Pretraining for Learning Transferable Representations, by Kiran Lekkala and 4 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2023-12 Change to browse by: cs cs.RO References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: 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

Related documents

• Value Explicit Pretraining for Learning Transferable Representations#189177
• Value Explicit Pretraining for Learning Transferable Representations#189077
• Value Explicit Pretraining for Learning Transferable Representations#189027
• A Fixed-Point Neural Operator for Size- and Functional-Transferable Hamiltonian Prediction#271888
• Pretraining Reusable Inference Across Views with Synthetic Task Priors#467117