English(EN)Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation: The Case of Multi-Armed Bandits
arXiv上的新研究推动了多臂老虎机算法和遗憾分析的进展 · 跟踪7个来源
作者PulseAugur 编辑部·[8 个来源]·
arXiv上发表的多篇研究论文探讨了多臂老虎机(MAB)算法的进展。其中一篇论文重新审视了具有线性函数逼近的Softmax策略梯度在多臂老虎机场景下的全局收敛性,确定了渐近收敛的条件。另一篇论文解决了具有反事实公平性约束的因果逻辑老虎机问题,建立了minimax最优遗憾界。进一步的研究介绍了最大化广义平均福利的物品在线公平分配算法,并探讨了“上升多臂老虎机”中对时间跨度感知的益处。此外,还有研究深入探讨了基于偏好的老虎机问题的复杂性,并分析了具有多个最优臂的老虎机问题,旨在改进遗憾保证。
AI
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…
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…
arXiv cs.LG
TIER_1English(EN)·Zongjun Yang, Rachitesh Kumar, Christian Kroer·
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…
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…
arXiv cs.AI
TIER_1English(EN)·Ahmed Ben Yahmed (CREST, ENSAE Paris, FAIRPLAY), Marc Abeille (FAIRPLAY), Cl\'ement Calauz\`enes (FAIRPLAY)·
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…
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…
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…
arXiv stat.ML
TIER_1English(EN)·Taehyun Hwang, Hyunjun Choi, Heesang Ann, Min-hwan Oh·
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…