{"slug": "adaptive-quantization-preserves-fast-rates-for-td-learning-over-rate-limited", "title": "Adaptive Quantization Preserves Fast Rates for TD Learning over Rate-Limited Channels", "summary": "A paper submitted to arXiv on 9 November 2026 introduces Batched Adaptively Quantized TD (BAQ-TD), an algorithm that preserves the convergence rate of unquantized temporal-difference learning over rate-limited channels. The authors prove a high-probability finite-time error bound showing that transmitting O(d log(T)) bits over a horizon of length T suffices to achieve the order-optimal rate of Õ(1/T) for a d-dimensional value function parameter, which the paper calls an exponential improvement in communication complexity over prior work. The result targets policy evaluation with linear function approximation in reinforcement learning subject to communication constraints.", "body_md": "# Computer Science > Machine Learning\n\n  [Submitted on 9 Nov 2026]\n\n# Title:Adaptive Quantization Preserves Fast Rates for TD Learning over Rate-Limited Channels\n\n[View PDF](http://arxiv.org/pdf/2611.12878v1)\n\nAbstract:Motivated by reinforcement learning subject to communication constraints, we study a policy evaluation problem with linear function approximation over a rate-limited channel. In our setup, an agent interacting with an unknown environment (modeled as a Markov Decision Process) transmits quantized estimates of a temporal-difference (TD) learning update direction to a server over a finite-capacity channel. Our goal is to investigate to what extent one can preserve the statistical convergence rates achievable when the channel has infinite capacity. To that end, we propose a new algorithm called Batched Adaptively Quantized TD (BAQ-TD), which uses batching to reduce the variance of the transmitted information, and adaptive quantization to encode innovations. We prove a high-probability finite-time error bound for BAQ-TD, and show that, above a certain finite channel capacity, BAQ-TD preserves the convergence rate of unquantized TD up to logarithmic factors. Specifically, for a $d$-dimensional value function parameter, we establish that transmitting a total of $\\mathcal{O}(d \\log(T))$ bits over a horizon of length $T$ suffices to achieve the order-optimal rate of $\\tilde{\\mathcal{O}}(1/T)$, marking an exponential improvement in communication-complexity over prior work.\n    \n\n### Additional Features\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\nIArxiv Recommender\n\n*(*[What is IArxiv?](https://iarxiv.org/about))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth 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.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/adaptive-quantization-preserves-fast-rates-for-td-learning-over-rate-limited", "canonical_source": "http://arxiv.org/abs/2611.12878v1", "published_at": "2026-11-10 15:26:52+00:00", "updated_at": "2026-11-10 15:53:01.087367+00:00", "lang": "en", "topics": ["machine-learning", "ai-research", "artificial-intelligence"], "entities": ["arXiv", "BAQ-TD", "Batched Adaptively Quantized TD"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/adaptive-quantization-preserves-fast-rates-for-td-learning-over-rate-limited", "markdown": "https://wpnews.pro/news/adaptive-quantization-preserves-fast-rates-for-td-learning-over-rate-limited.md", "text": "https://wpnews.pro/news/adaptive-quantization-preserves-fast-rates-for-td-learning-over-rate-limited.txt", "jsonld": "https://wpnews.pro/news/adaptive-quantization-preserves-fast-rates-for-td-learning-over-rate-limited.jsonld"}}