New research on arXiv advances multi-armed bandit algorithms and regret analysis · 7 sources tracked

COVERAGE [8]

1. arXiv cs.LG TIER_1 English(EN) · Max Qiushi Lin, Jincheng Mei, Matin Aghaei, Michael Lu, Bo Dai, Alekh Agarwal, Dale Schuurmans, Csaba Szepesvari, Sharan Vaswani · 2026-10-03 04:00

   Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation: The Case of Multi-Armed Bandits

   arXiv:2505.03155v2 Announce Type: replace Abstract: Policy gradient (PG) methods have played an essential role in the empirical successes of reinforcement learning. In order to handle large state-action spaces, PG methods are typically used with function approximation. In this se…

2. arXiv cs.LG TIER_1 English(EN) · Junhyuk Huh, Seoungbin Bae, Dabeen Lee · 2026-10-03 04:00

   Minimax Optimal Regret for Causal Logistic Bandits with Counterfactual Fairness

   arXiv:2610.01377v1 Announce Type: new Abstract: We study causal logistic bandits with counterfactual fairness constraints. The causal structure is given through known factual and counterfactual feature maps that share an unknown logistic reward parameter, but the learner observes…

3. arXiv cs.LG TIER_1 English(EN) · Zongjun Yang, Rachitesh Kumar, Christian Kroer · 2026-10-03 04:00

   Online Generalized-Mean Welfare Maximization: Achieving Near-Optimal Regret from Samples

   arXiv:2602.10469v2 Announce Type: replace-cross Abstract: We study online fair allocation of $T$ sequentially arriving items among $n$ agents with heterogeneous preferences, with the objective of maximizing generalized-mean welfare, defined as the $p$-mean of agents' time-average…

4. arXiv cs.LG TIER_1 English(EN) · Seockbean Song, Chenyu Gan, Youngsik Yoon, Siwei Wang, Wei Chen, Jungseul Ok · 2026-10-02 04:00

   Rising Multi-Armed Bandits with Known Horizons

   arXiv:2602.10727v3 Announce Type: replace Abstract: Rising Multi-Armed Bandits (RMABs) model sequential decision problems where each arm's expected reward improves with repeated pulls. In such problems, the value of investing in an arm depends on how much time remains, making kno…

5. arXiv cs.AI TIER_1 English(EN) · Ahmed Ben Yahmed (CREST, ENSAE Paris, FAIRPLAY), Marc Abeille (FAIRPLAY), Cl\'ement Calauz\`enes (FAIRPLAY) · 2026-10-01 04:00

   On the Complexity of Preference-Based Bandits

   arXiv:2609.39351v1 Announce Type: new Abstract: We study preference-based bandits with general reward function classes, where a learner sequentially selects pairs of arms and observes binary preference feedback governed by the Bradley--Terry model. This setting naturally arises i…

6. arXiv cs.AI TIER_1 English(EN) · Kaixuan Ji, Qiwei Di, Qingyue Zhao, Heyang Zhao, Quanquan Gu · 2026-10-01 04:00

   Bandits with Multiple Optimal Arms: Minimax Regret and Non-Adaptivit

   arXiv:2609.38659v1 Announce Type: cross Abstract: We study multi-armed bandits (MAB) with multiple optimal arms, motivated by the fact that many practical decision making problems admit multiple correct answers. For $K$-armed bandits with $A$ optimal arms, we first provide a shar…

7. arXiv stat.ML TIER_1 English(EN) · Nam Nguyen, Tuan Quang Dam · 2026-10-02 04:00

   Sharp Non-Asymptotic Analysis of the Penalized Challenger in $\beta$-EB-TCI for Bernoulli Bandits

   arXiv:2610.01951v1 Announce Type: cross Abstract: Top-two algorithms are simple and effective for fixed-confidence best-arm identification, but their sharp non-asymptotic behavior is still not well understood. We study this problem for Bernoulli bandits through $\beta$-EB-TCI, th…

8. arXiv stat.ML TIER_1 English(EN) · Taehyun Hwang, Hyunjun Choi, Heesang Ann, Min-hwan Oh · 2026-10-02 04:00

   Block Optimism for Nonstationary Bandits with Latent Linear Dynamics

   arXiv:2610.00911v1 Announce Type: new Abstract: We study an endogenous nonstationary stochastic bandit problem with latent linear dynamics, where actions affect both immediate rewards and the future evolution of an unobserved latent state. Rewards are bilinear in the current acti…