method · first seen 5 Oct 2026
upper confidence bound
Also: UCB, Bayes-UCBVI, uncertainty-adjusted optimism, upper confidence bound exploration
An exploration strategy that selects actions by optimistic estimates of their reward plus a confidence term.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Bellman-Centric Learning: Near-Optimal Regret for Linear Bandits with MemoryPapers · 5 Oct 2026 · Jingyuan Liu, Huiwen Jia
- A Query Is Not a Commitment: Learning to Correct Expert Answers in Online DeferralPapers · 5 Oct 2026 · Yannis Montreuil, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi
- Dynamic Minimax Regret Optimization for Robust LLM Post-TrainingPapers · 5 Oct 2026 · Chengbo Zang, Haoyu Dong, Mehmet Kerem Turkcan, Gil Zussman, Zoran Kostic, Javad…
- Accelerating Linear Bandits with Persistent Candidate SetsPapers · 9 Oct 2026 · Bingkui Tong, Daria Korovaitceva, Marina Sheshukova, Sergey Samsonov, Junpei Kom…
- What Information Buys in Active InferencePapers · 13 Oct 2026 · Melih Kandemir, Mustafa Mert Çelikok
- Minimax estimation of the pseudo-spectral gap of continuous Markov chains, with applications to empirical concentration boundsPapers · 14 Oct 2026 · Vahe Karagulyan, Mikołaj Kasprzak, Pierre Alquier
Latest sources
- Uncertainty-Aware Hybrid Offline Reinforcement Learning with Online Action Selection Enabled by Sparse Gaussian-Process CriticsPapers · 10 Nov 2026 · Marco Chan, Christos Evripidou, Liqiu Dong, Benoit Chachuat, Mehmet Mercangöz
- UCB-min: Combining Bandits Under Variance Heterogeneity (Extended Version)Papers · 9 Nov 2026 · Lilia Izri, Benoit Groz, Silviu Maniu
- Online Causal Configuration for Networked Systems via Doubly Robust Steady-State LearningPapers · 6 Nov 2026 · Yuli Liu, Zhiheng Zhang
- MEMOIR: A Training-Free Memory Lifecycle for Long-Horizon LLM AgentsPapers · 5 Nov 2026 · Mayank Anand, Subham Raj, Aman Vaibhav Jha, Sriparna Saha
- Optimal Learning in Fairness-Aware Contextual BanditsPapers · 31 Oct 2026 · Gengyu Xue, Fan Wang, Feiyu Jiang, Zifeng Zhao, Yi Yu
- Fair Recommender Systems for Intersecting GroupsPapers · 29 Oct 2026 · Christine Ling, Juba Ziani
- Cascading Bandits with Noisy Observations: Algorithms and Regret BoundsPapers · 21 Oct 2026 · Yashaswini Kaluguri, Nikhil Karamchandani
- Learning Personalized Memory Gating from Delayed One-Sided FeedbackPapers · 16 Oct 2026 · Kaixuan Ji, Zixiang Chen, Wenting Zhao, Cheng Qian, Heng Wang, Weizhi Zhang, Jie…
- The Tilted Sampling Problem: Optimism, Posterior Sampling, and Logarithmic RegretPapers · 15 Oct 2026 · Mohammad Pedramfar, Siamak Ravanbakhsh
- Minimax estimation of the pseudo-spectral gap of continuous Markov chains, with applications to empirical concentration boundsPapers · 14 Oct 2026 · Vahe Karagulyan, Mikołaj Kasprzak, Pierre Alquier
- What Information Buys in Active InferencePapers · 13 Oct 2026 · Melih Kandemir, Mustafa Mert Çelikok
- Accelerating Linear Bandits with Persistent Candidate SetsPapers · 9 Oct 2026 · Bingkui Tong, Daria Korovaitceva, Marina Sheshukova, Sergey Samsonov, Junpei Kom…