The paper investigates preference-based bandits where a learner selects pairs of arms and receives binary preference feedback modeled by Bradley–Terry. It introduces the locally sensitive eluder dimension, a new complexity measure for logistic preference feedback, and proposes the GINOP algorithm that uses log-loss confidence sets to balance optimism and exploration. The authors prove a first-order regret bound showing that learning with preference feedback can be as statistically efficient as learning from direct rewards, and they validate their theory with empirical experiments.
By Ahmed Ben Yahmed (CREST, ENSAE Paris, FAIRPLAY), Marc Abeille (FAIRPLAY), Cl\'ement Calauz\`enes (FAIRPLAY)
arXiv:2607. 15577v1 Announce Type: cross Abstract: Causal bandits exploit structural relationships among variables to share information across interventions and accelerate the identification of high-reward decisions.
By Muhammad Qasim Elahi, Murat Kocaoglu, Mahsa Ghasemi
arXiv:2502. 06577v3 Announce Type: replace-cross Abstract: Causal knowledge can be used to support decision-making problems.
By Francisco N. F. Q. Simoes, Itai Feigenbaum, Mehdi Dastani, Thijs van Ommen
arXiv:2607. 28408v1 Announce Type: new Abstract: This thesis studies policy learning in interactive systems where an agent observes a context, selects an action from a very large set, and receives partial feedback.
By Imad Aouali
The paper introduces Latent Order Bandits (LOB), a new bandit framework that relaxes the strict assumptions of traditional latent bandits by only requiring a partial order of action preferences within each latent state. LOB allows instances sharing the same state to have different reward distributions as long as the action ranking remains consistent, making it suitable for scenarios like user groups on streaming services who agree on genre preferences but rate differently. The authors present an upper‑confidence bound algorithm for both total and partial latent orders, provide regret bounds, and propose a posterior‑sampling variant that empirically outperforms full‑prior latent bandits when reward scales vary across instances sharing the same latent state.
By Emil Carlsson, Newton Mwai, Fredrik D. Johansson
arXiv:2607. 08971v1 Announce Type: new Abstract: The stochastic linear bandit, where actions are represented as vectors and rewards are linear, is a central paradigm for sequential decision making.
By Gautam Dasarathy, Vineet Gattani, Lalit Jain
arXiv:2610.32910v1 Announce Type: new
Abstract: Regularised reinforcement learning (RL) algorithms rely on estimators, like Monte Carlo tree search or one-step look-ahead, to provide policy, value, o...
By Danilo Vucetic, Alexandre Larouche, Mohammad Pedramfar, Audrey Durand, Gauthier Gidel
arXiv:2606. 14929v1 Announce Type: cross Abstract: Modern recommendation systems increasingly rely on dynamically routing diverse queries to multiple embedding models.
By Yan Dai, Negin Golrezaei, Patrick Jaillet
arXiv:2209. 15448v3 Announce Type: replace Abstract: As AI becomes more prevalent throughout society, effective methods of integrating humans and AI systems that leverage their respective strengths and mitigate risk have become an important priority.
By Jiayi Wang, Zhengling Qi, Chengchun Shi
arXiv:2606. 00367v1 Announce Type: cross Abstract: Reinforcement learning problems typically define the goal as maximizing the expected value of a scalar reward function.
By Jonathan Cola\c{c}o Carr, Prakash Panangaden, Doina Precup, Benjamin Van Roy
arXiv:2606. 19328v1 Announce Type: cross Abstract: Preference-based RL provides an approach to learning reward models from pairwise comparisons of behaviors, bypassing the need for explicit reward design.
By Mohamed Nabail, Leo Cheng, Jingmin Wang, Nicholas Rhinehart
arXiv:2604. 00531v2 Announce Type: replace Abstract: Multi-task representation learning exploits the shared structure among related tasks by learning a common latent representation, thereby improving sample efficiency.
By Jiabin Lin, Shana Moothedath