·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
How long is Anthropic’s lease with SpaceX? Opinions vary.1h◆Sesame, the conversational AI startup from Oculus founders, launches its iOS app1h◆Sneak peek at new Siri app reveals Apple’s plans to take on ChatGPT and more1h◆These new iOS 27 renders hint at Siri’s big redesign2h◆RSI is the new AGI — and it’s just as hard to pin down2h◆At TechCrunch Disrupt 2026: Databricks’ co-founder on what kills enterprise AI deals2h◆YouTube adds new podcast features, including an AI recommendation tool and ‘Auto speed’2h◆CNN sues Perplexity over ‘verbatim’ copycat articles2h◆Rivian’s software chief thinks you don’t need CarPlay or buttons2h◆2 days left: Lock in ticket savings of up to $410 to TechCrunch Disrupt 20262h◆Visa invests in Replit to power agentic payments for developers2h◆Has the hunt for AI compute uncovered the next Cerebras?3h◆The AI Hype Index: AI gets booed in graduation season6h◆YouTube will let you ask AI to make a custom video feed7h◆Vertu wants CEOs to run companies from an AI foldable starting at $6,8809h◆Laguna M.1/XS.2 Technical Report12h◆GradientStabilizer:Fix the Norm, Not the Gradient12h◆A Unified Framework for the Evaluation of LLM Agentic Capabilities12h◆LNN-PINN: A Unified Physics-Only Training Framework with Liquid Residual Blocks12h◆AssertLLM2: A Comprehensive LLM Benchmark for Assertion Generation from Design Specifications12h◆How long is Anthropic’s lease with SpaceX? Opinions vary.1h◆Sesame, the conversational AI startup from Oculus founders, launches its iOS app1h◆Sneak peek at new Siri app reveals Apple’s plans to take on ChatGPT and more1h◆These new iOS 27 renders hint at Siri’s big redesign2h◆RSI is the new AGI — and it’s just as hard to pin down2h◆At TechCrunch Disrupt 2026: Databricks’ co-founder on what kills enterprise AI deals2h◆YouTube adds new podcast features, including an AI recommendation tool and ‘Auto speed’2h◆CNN sues Perplexity over ‘verbatim’ copycat articles2h◆Rivian’s software chief thinks you don’t need CarPlay or buttons2h◆2 days left: Lock in ticket savings of up to $410 to TechCrunch Disrupt 20262h◆Visa invests in Replit to power agentic payments for developers2h◆Has the hunt for AI compute uncovered the next Cerebras?3h◆The AI Hype Index: AI gets booed in graduation season6h◆YouTube will let you ask AI to make a custom video feed7h◆Vertu wants CEOs to run companies from an AI foldable starting at $6,8809h◆Laguna M.1/XS.2 Technical Report12h◆GradientStabilizer:Fix the Norm, Not the Gradient12h◆A Unified Framework for the Evaluation of LLM Agentic Capabilities12h◆LNN-PINN: A Unified Physics-Only Training Framework with Liquid Residual Blocks12h◆AssertLLM2: A Comprehensive LLM Benchmark for Assertion Generation from Design Specifications12h◆
News/Sparse Offline Reinforcement Learning with Corruption Robustness
arxiv
PublishedMay 13, 2026 at 4:00 AM

Sparse Offline Reinforcement Learning with Corruption Robustness

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

arXiv:2512.24768v3 Announce Type: replace-cross Abstract: We investigate robustness to strong data corruption in offline sparse reinforcement learning (RL). In our setting, an adversary may arbitrarily perturb a fraction of the collected trajectories from a high-dimensional but sparse Markov decisio

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

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

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
arxivLaguna M.1/XS.2 Technical Report12harxivGradientStabilizer:Fix the Norm, Not the Gradient12harxivA Unified Framework for the Evaluation of LLM Agentic Capabilities12harxivLNN-PINN: A Unified Physics-Only Training Framework with Liquid Residual Blocks12h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

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

Originally published on arxiv ↗
HomeModelsNews