Optimal Control with Natural Images: Efficient Reinforcement Learning using Overcomplete Sparse Codes

[2412.08893] Optimal Control with Natural Images: Efficient Reinforcement Learning using Overcomplete Sparse Codes Skip to main content Search Submit Donate Log in Computer Science > Machine Learning arXiv:2412.08893 (cs) [Submitted on 12 Dec 2024 ( v1 ), last revised 5 May 2026 (this version, v3)] Title: Optimal Control with Natural Images: Efficient Reinforcement Learning using Overcomplete Sparse Codes Authors: Peter N. Loxley View PDF HTML (experimental) Abstract: Optimal control and sequential decision making are widely used in many complex tasks. Optimal control over a sequence of natural images is a first step towards understanding the role of vision in control. Here, we formalize this problem as a reinforcement learning task, and derive general conditions under which an image includes enough information to implement an optimal policy. Reinforcement learning is shown to provide a computationally efficient method for finding optimal policies when natural images are encoded into "efficient" image representations. This is demonstrated by introducing a new reinforcement learning benchmark that easily scales to large numbers of states and long horizons. In particular, by representing each image as an overcomplete sparse code, we are able to efficiently solve an optimal control task that is orders of magnitude larger than those tasks solvable using complete codes. Theoretical justification for this behaviour is provided. This work also demonstrates that deep learning is not necessary for efficient optimal control with natural images. Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Systems and Control (eess.SY) Cite as: arXiv:2412.08893 [cs.LG] (or arXiv:2412.08893v3 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2412.08893 Focus to learn more arXiv-issued DOI via DataCite Related DOI : https://doi.org/10.1016/j.neucom.2026.134840 Focus to learn more DOI(s) linking to related resources Submission history From: Peter Loxley [ view email ] [v1] Thu, 12 Dec 2024 03:14:47 UTC (113 KB) [v2] Wed, 24 Dec 2025 04:42:33 UTC (111 KB) [v3] Tue, 5 May 2026 23:38:18 UTC (8,432 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 | 2024-12 Change to browse by: cs cs.AI cs.SY eess eess.SY 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)

Related documents

• Optimal Control with Natural Images: Efficient Reinforcement Learning using Overcomplete Sparse Codes#677346
• Contraction-Aware Reinforcement Learning for Nonlinear Control with Statistical Robustness#612794
• Contraction-Aware Reinforcement Learning for Nonlinear Control with Statistical Robustness#611317
• HPO: Hysteretic Policy Optimization for Stable and Efficient Training under Sparse-Reward Regime#238618
• Maximum Likelihood Reinforcement Learning#652193