·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Replit’s CEO says the future of work is the ‘self-driving company’1h◆Bridging the Gap: Converting Read Text to Conversational Dialogue10h◆Sharp and Stable Label-Free Calibration Certificates from Logical Coherence10h◆Backward Compatibility in Zero-Bit Neural Audio Watermarking10h◆Disagreement-Guided Weak-to-Strong Routing10h◆One Is Not Enough: How People Use Multiple AI Models in Everyday Life10h◆L2G-SR: Learning to Guide LLM-based Symbolic Regression10h◆Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents10h◆Unfragmenting Nawatl NMT: Single-Variant Specialization for Masewalkopa10h◆Kolab: Benchmarking Human-Agent Collaboration in Long-Horizon Workflows10h◆Can Visual Generation Expand What Unified Multimodal Models Know?10h◆Whole-Body Dexterity10h◆Beyond Downstream QA: Rethinking How We Evaluate Agent Memory10h◆CompMat-Bench: Benchmarking AI Agents for Computational Materials Science10h◆LLMR: Knowledge Distillation with a Large Language Model-Induced Reward10h◆PRISM: PRIvileged Sibling-guided Multi-Agent Topology Design10h◆Does Personalization Break Trust? Open-Set Rejection Calibration Under Few-Shot On-Device Intent Adaptation10h◆Training Reasoning Models to Generate Diverse Scientific Ideas10h◆Linear Independence of Polynomial Compositions with Bounded Input Degree10h◆Do LLMs have core beliefs?10h◆Replit’s CEO says the future of work is the ‘self-driving company’1h◆Bridging the Gap: Converting Read Text to Conversational Dialogue10h◆Sharp and Stable Label-Free Calibration Certificates from Logical Coherence10h◆Backward Compatibility in Zero-Bit Neural Audio Watermarking10h◆Disagreement-Guided Weak-to-Strong Routing10h◆One Is Not Enough: How People Use Multiple AI Models in Everyday Life10h◆L2G-SR: Learning to Guide LLM-based Symbolic Regression10h◆Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents10h◆Unfragmenting Nawatl NMT: Single-Variant Specialization for Masewalkopa10h◆Kolab: Benchmarking Human-Agent Collaboration in Long-Horizon Workflows10h◆Can Visual Generation Expand What Unified Multimodal Models Know?10h◆Whole-Body Dexterity10h◆Beyond Downstream QA: Rethinking How We Evaluate Agent Memory10h◆CompMat-Bench: Benchmarking AI Agents for Computational Materials Science10h◆LLMR: Knowledge Distillation with a Large Language Model-Induced Reward10h◆PRISM: PRIvileged Sibling-guided Multi-Agent Topology Design10h◆Does Personalization Break Trust? Open-Set Rejection Calibration Under Few-Shot On-Device Intent Adaptation10h◆Training Reasoning Models to Generate Diverse Scientific Ideas10h◆Linear Independence of Polynomial Compositions with Bounded Input Degree10h◆Do LLMs have core beliefs?10h◆
News/Sharp Statistical Rates for Asynchronous TD Learning with Markovian Data
arxiv
PublishedOctober 2, 2026 at 4:00 AM
—neutral

Sharp Statistical Rates for Asynchronous TD Learning with Markovian Data

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2609.38880v1 Announce Type: cross Abstract: We study the last iterate of standard tabular temporal-difference (TD) learning from a single trajectory of a finite Markov reward process. For discount factor $\gamma$, write $H=(1-\gamma)^{-1}$, and let $\mu_{\min}$ and $t_{\operatorname{mix}}$ den

Stay posted· Newsletter

Three short emails a week: Monday, Wednesday and Friday. Top movers, new models and the most-referenced story.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivBridging the Gap: Converting Read Text to Conversational Dialogue10harxivSharp and Stable Label-Free Calibration Certificates from Logical Coherence10harxivBackward Compatibility in Zero-Bit Neural Audio Watermarking10harxivDisagreement-Guided Weak-to-Strong Routing10h
The Bubble Brief
MON · WED · FRI

Read AI insights every Monday, Wednesday and Friday — top movers, new models, story of the week.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Originally published on arxiv ↗
PrivacyTermsRefundsLegal notice|AboutMethodologyContact

© 2026 Databubble

Built by Marouane Gazouzi · Readyo, AI interview coach

HomeModelsNews