Close Menu
techwavedispatch.com

    Subscribe to Updates

    Get the latest creative news from FooBar about art, design and business.

    What's Hot

    NASA’s new Moon plan is taking shape, but some big questions remain

    November 20, 2026

    Daniel Ek backs AI researcher’s fusion power startup. Here’s what they’re building.

    November 20, 2026

    Change These Settings If You Want GTA 6 To Feel Like Old GTA

    November 20, 2026
    Facebook X (Twitter) Instagram
    Trending
    • NASA’s new Moon plan is taking shape, but some big questions remain
    • Daniel Ek backs AI researcher’s fusion power startup. Here’s what they’re building.
    • Change These Settings If You Want GTA 6 To Feel Like Old GTA
    • [2610.14988] Mixing Regularization for Average-Reward $Q$-Learning and $Q$-Planning
    • What Happened to Silicon Valley? – O’Reilly
    • Grounding Spatial Intelligence in Action with Interactive CAPTCHAs
    • Prisons get OK to jam contraband phones. CTIA says nearby phones will be jammed too.
    • Jensen Huang’s ‘Lying’ Alarmed Nvidia Board Ahead of His Resignation
    Facebook X (Twitter) Instagram
    techwavedispatch.com
    Subscribe
    Friday, November 20
    • Home
    • AI Tools & Software
    • Machine Learning
    • Generative AI
    • Robotics & Automation
    • Future Tech & Hardware
    • AI in Business
    • Ethics & Regulations
    • More
      • Gadgets & Smart Devices
      • Cybersecurity & AI
      • Tech Breakthroughs
    techwavedispatch.com
    Home»Machine Learning»[2610.14988] Mixing Regularization for Average-Reward $Q$-Learning and $Q$-Planning
    Machine Learning

    [2610.14988] Mixing Regularization for Average-Reward $Q$-Learning and $Q$-Planning

    adminBy adminNovember 20, 2026No Comments2 Mins Read
    Facebook Twitter Pinterest LinkedIn Tumblr Email
    [2610.14988] Mixing Regularization for Average-Reward $Q$-Learning and $Q$-Planning
    Share
    Facebook Twitter LinkedIn Pinterest Email

    [Submitted on 10 Oct 2026 (v1), last revised 19 Nov 2026 (this version, v2)]

    View a PDF of the paper titled Mixing Regularization for Average-Reward $Q$-Learning and $Q$-Planning, by Julien Roger and 3 other authors

    View PDF
    HTML (experimental)

    Abstract:The average-reward setting for reinforcement learning is challenging because, without discounting, the span-contraction of the Bellman operator depends on the mixing properties of the underlying Markov dynamics. Whereas existing work typically assumes contraction, for instance through environment mixing, we study regularization toward a given reward-agnostic, $m$-step mixing policy to control the mixing properties of the learned policy. Our central mixing lemma quantifies how the reference policy’s mixing properties transfer to the resulting learned policies. In particular, a single regularizer-dependent quantity simultaneously controls the contraction of the regularized Bellman operator and the exploration of the resulting policies. A second regularizer-dependent quantity controls the bias introduced by regularization, revealing a trade-off between convergence speed and approximation accuracy. Building on this result, we establish finite-time guarantees for regularized $Q$-iteration, synchronous and single-trajectory $Q$-learning, and $Q$-planning. Under one-step mixing, our bounds for approximating the regularized fixed point match the classical model-query bound for relative value iteration and, up to logarithmic factors, an existing sample-complexity bound for synchronous $Q$-learning. We also establish finite-time guarantees under multi-step mixing. For $Q$-planning, we characterize how the planning horizon trades off boundary bias against sample complexity. Finally, we present numerical studies validating the analysis: (i) knowledge of a strong mixing policy improves convergence and exploration, with larger benefits under more severe bottlenecks; and (ii) the observed rankings of $\alpha$-divergence regularizers by bias and convergence speed are consistent with our theoretical analysis.

    Submission history

    From: Julien Roger [view email]
    [v1]
    Sat, 10 Oct 2026 15:06:10 UTC (808 KB)
    [v2]
    Thu, 19 Nov 2026 15:09:50 UTC (946 KB)

    AverageReward Mixing QLearning QPlanning Regularization
    Share. Facebook Twitter Pinterest LinkedIn Tumblr Email
    admin
    • Website

    Related Posts

    Grounding Spatial Intelligence in Action with Interactive CAPTCHAs

    November 20, 2026

    [2609.37789] Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance

    November 20, 2026

    How Standard Bank Group automates AI risk assessment for generative AI

    November 20, 2026
    Leave A Reply Cancel Reply

    Top Posts

    NVIDIA Is Investigating Reports That CEO Jensen Huang Was The Target Of Chinese Spy Efforts

    November 8, 202619 Views

    ADIndex: Layer-Adaptive Sparse Attention Indexing via Group-Level Distillation

    November 11, 20265 Views

    Anthropic releases new Mythos and Fable models amid RSI concerns

    November 9, 20265 Views

    If AGI is so close, why is everyone leaving? The neolabs and their bets

    November 6, 20265 Views
    Don't Miss
    Tech Breakthroughs

    NASA’s new Moon plan is taking shape, but some big questions remain

    By adminNovember 20, 20260

    Propellant transfer on tap For Starship, orbital refueling remains the key to the Moon. SpaceX’s…

    Daniel Ek backs AI researcher’s fusion power startup. Here’s what they’re building.

    November 20, 2026

    Change These Settings If You Want GTA 6 To Feel Like Old GTA

    November 20, 2026

    [2610.14988] Mixing Regularization for Average-Reward $Q$-Learning and $Q$-Planning

    November 20, 2026
    About Us

    Welcome to TechWave Dispatch

    At TechWave Dispatch, we bring you the latest news, insights, and developments from the ever-evolving world of technology. Our mission is to keep readers informed about the innovations shaping our digital future.

    From artificial intelligence and machine learning to cybersecurity, robotics, smart devices, and groundbreaking technologies, we cover the topics that matter in today's fast-moving tech landscape.

    Our Picks

    NASA’s new Moon plan is taking shape, but some big questions remain

    November 20, 2026

    Daniel Ek backs AI researcher’s fusion power startup. Here’s what they’re building.

    November 20, 2026

    Change These Settings If You Want GTA 6 To Feel Like Old GTA

    November 20, 2026
    Most Popular

    After blocking Muse, Amazon now lets users text Alexa to help them shop

    November 6, 20260 Views

    A controlled world for robot learning and evaluation

    November 6, 20260 Views

    Egyptian and Nigerian English join the Open ASR Leaderboard

    November 6, 20260 Views
    Facebook X (Twitter) Instagram Pinterest
    • Terms and Conditions
    • Privacy Policy
    • Contact Us
    • About Us
    © 2026 TechWave Dispatch. All Rights Reserved.

    Type above and press Enter to search. Press Esc to cancel.