·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
NeoMME: an efficient Multimodal-native and Multilingual Encoder2h◆Nvidia confirms it will buy Hugging Face for $12.9 billion2h◆Nvidia is buying Hugging Face for almost $13 billion3h◆Meta-ethics and AI: exploring the novel meta-ethical questions in the era of AI11h◆SSAKG 2.0: An Open-Source Package for Structural Associative Sequence Memory and Context-Based Retrieval11h◆Epistemic Sybil Resistance: Multiplying AI Agents Without Multiplying Evidence11h◆DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents11h◆MASkills: Continual Skills Optimization for Multi-Agent LLM Systems11h◆Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model11h◆SpecMine: A Large-Scale Corpus of Spec-Driven Development Artifacts11h◆Elite political incivility is rising across democracies11h◆Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation11h◆Sim2Signal: Sim-to-Real Benchmarks for Traffic Signal Control11h◆Recursive Value Learning for Long-Horizon Offline Goal-Conditioned RL11h◆Similarity-Aware Personalized Federated Learning in Heterogeneous Environments11h◆Oracle, will I ever learn? A study of prediction convergence and complementarity across link prediction models11h◆UE5M3 FP4 Block Scaling for Stable Language Model Pretraining11h◆Network-Aware Forecasting on Wireless Access Points11h◆Monotonic anomaly detection11h◆Cantelli Constrained Policy Optimization11h◆NeoMME: an efficient Multimodal-native and Multilingual Encoder2h◆Nvidia confirms it will buy Hugging Face for $12.9 billion2h◆Nvidia is buying Hugging Face for almost $13 billion3h◆Meta-ethics and AI: exploring the novel meta-ethical questions in the era of AI11h◆SSAKG 2.0: An Open-Source Package for Structural Associative Sequence Memory and Context-Based Retrieval11h◆Epistemic Sybil Resistance: Multiplying AI Agents Without Multiplying Evidence11h◆DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents11h◆MASkills: Continual Skills Optimization for Multi-Agent LLM Systems11h◆Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model11h◆SpecMine: A Large-Scale Corpus of Spec-Driven Development Artifacts11h◆Elite political incivility is rising across democracies11h◆Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation11h◆Sim2Signal: Sim-to-Real Benchmarks for Traffic Signal Control11h◆Recursive Value Learning for Long-Horizon Offline Goal-Conditioned RL11h◆Similarity-Aware Personalized Federated Learning in Heterogeneous Environments11h◆Oracle, will I ever learn? A study of prediction convergence and complementarity across link prediction models11h◆UE5M3 FP4 Block Scaling for Stable Language Model Pretraining11h◆Network-Aware Forecasting on Wireless Access Points11h◆Monotonic anomaly detection11h◆Cantelli Constrained Policy Optimization11h◆
News/Minimax Optimal Variance-Aware Regret Bounds for Multinomial Logistic MDPs
arxiv
PublishedMay 21, 2026 at 4:00 AM
—neutral

Minimax Optimal Variance-Aware Regret Bounds for Multinomial Logistic MDPs

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

arXiv:2605.19768v1 Announce Type: new Abstract: We study reinforcement learning for episodic Markov Decision Processes (MDPs) whose transitions are modelled by a multinomial logistic (MNL) model. Existing algorithms for MNL mixture MDPs yield a regret of $\smash{\tilde{O}(dH^2\sqrt{T})}$ (Li et al.,

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
arxivMeta-ethics and AI: exploring the novel meta-ethical questions in the era of AI11harxivSSAKG 2.0: An Open-Source Package for Structural Associative Sequence Memory and Context-Based Retrieval11harxivEpistemic Sybil Resistance: Multiplying AI Agents Without Multiplying Evidence11harxivDocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents11h
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