We design and analyze \underline{M}echanism-\underline{E}nforced \underline{S}equential \underline{HA}lving (MESHA), an algorithm for Best Arm Identification (BAI) in strategic linear bandits. In this setting, each arm may strategically misreport its feature vector to maximize the probability of being identified as the best arm, when rewards are generated from the arms' true but unobservable features.
arXiv:2606. 01799v1 Announce Type: new Abstract: We study $N$-armed stochastic dueling bandits under the Condorcet-winner assumption, where three widely adopted objectives are considered: best-arm identification (BAI), weak regret, and strong regret.
By Pu Wang, Yao-Xiang Ding
arXiv:2605. 01752v4 Announce Type: replace Abstract: We study linear dueling bandits in volatile environments characterized by the simultaneous presence of post-serving contexts, delayed feedback, and adversarial corruption.
By Youngmin Oh
arXiv:2606. 09002v1 Announce Type: cross Abstract: We study a stochastic multi-armed bandit problem in which the set of available arms expands over time.
By Deqi Zheng, Xiaoyang Xu, Yuhong Yang
arXiv:2409. 18909v2 Announce Type: replace Abstract: Motivated by real-world applications that necessitate responsible experimentation, we introduce the problem of best arm identification (BAI) with minimal regret.
By Junwen Yang, Vincent Y. F. Tan, Tianyuan Jin
arXiv:2605. 20854v2 Announce Type: replace Abstract: We study a stochastic bandit algorithm motivated by retry-aware objectives that value the best outcome among multiple attempts, such as pass@$k$ and max@$k$.
By Bingkui Tong, Junpei Komiyama, Soichiro Nishimori, Paavo Parmas
arXiv:2608. 01545v1 Announce Type: cross Abstract: We study the problem of identifying the dominant arm in multi-armed bandits, where the objective is to find the action with the highest probability of exceeding the realized rewards of all other actions.
By Jonghyun Sim, Wonyoung Kim
arXiv:2602. 09456v2 Announce Type: replace Abstract: We propose an algorithmic framework, Offline Estimation to Decisions (OE2D), that efficiently reduces contextual bandit learning with general reward function approximation to offline regression.
By Hao Qin, Chicheng Zhang
arXiv:2605. 01961v2 Announce Type: replace Abstract: Learning from human preference data is becoming a useful tool, from fine-tuning large language models to training reinforcement learning agents.
By Maheed H. Ahmed, Mahsa Ghasemi
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.
arXiv:2409. 05980v2 Announce Type: replace-cross Abstract: Rested and Restless Bandits are two well-known bandit settings that are useful to model real-world sequential decision-making problems in which the expected reward of an arm evolves over time due to the actions we perform or due to the nature.
By Gianmarco Genalti, Marco Mussi, Nicola Gatti, Marcello Restelli, Matteo Castiglioni, Alberto Maria Metelli
arXiv:2606. 19883v1 Announce Type: new Abstract: We study a multi-agent multi-armed bandit problem in the competitive setup with two-sided matching markets under a human centric decision making model.
By Ananya Kunisetty, Avishek Ghosh