arXiv:2608. 10529v1 Announce Type: cross Abstract: The multi-armed bandit problem is a central framework in sequential decision-making, extensively studied under sub-Gaussian reward assumptions.
By Daphne Feng, Ricardo Parada, Lily Jiang, Sophia Yi, William Chang
arXiv:2606. 04305v1 Announce Type: new Abstract: We study online learning with an additional offline dataset in the stochastic linear bandit setting.
By Kushagra Chandak, Toshinori Kitamura, Xiaoqi Tan
In many online learning and bandit problems, the actions we consider possess inherent similarities--for instance because they share latent traits, tags, or hierarchical structure. We study online learning with a similarity-structured action set, encoded by a rooted tree whose leaves are the actions and whose levels quantify how closely two actions are related.
arXiv:2502. 08870v2 Announce Type: replace Abstract: We provide an approach for the analysis of randomised exploration algorithms like Thompson sampling that does not rely on forced optimism or posterior inflation.
By Marc Abeille, David Janz, Ciara Pike-Burke
arXiv:2604. 00523v2 Announce Type: replace Abstract: We study for the first time, stochastic dueling bandits over continuous action spaces with Lipschitz structure, where feedback is purely comparative.
By Mudit Sharma, Shweta Jain, Vaneet Aggarwal, Ganesh Ghalme
We study the contextual combinatorial semi-bandit (CCSB) problem with general reward function approximation. At each round, the learner observes a context, selects a combinatorial action consisting of a subset of basic arms, and receives the reward of each selected arm; the goal is to maximize the cumulative reward over time.