arXiv Machine Learning July 27, 2026 By Yuta Natsubori, Masataka Ushiku, Yuta Saito

Cross-Domain Off-Policy Evaluation and Learning for Contextual Bandits

Read the original on arXiv Machine Learning →

arXiv:2607. 22012v1 Announce Type: new Abstract: Off-Policy Evaluation and Learning (OPE/L) in contextual bandits is rapidly gaining popularity in real systems because new policies can be evaluated and learned securely using only historical logged data.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

reinforcement-learning

arXiv Machine Learning

Jun 2

Off-Policy Learning in Large Action Spaces: Optimization Matters More Than Estimation

arXiv:2509. 03456v2 Announce Type: replace-cross Abstract: Off-policy evaluation (OPE) and off-policy learning (OPL) are foundational for decision-making in offline contextual bandits.

By Imad Aouali, Otmane Sakhi

arXiv Machine Learning

Jul 31

On-Policy and Off-Policy Learning for Large Action Spaces

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

agents diffusion safety

arXiv Machine Learning

1d ago

Sequential Batch Learning in Finite-Action Linear Contextual Bandits

arXiv:2004. 06321v2 Announce Type: replace Abstract: We study the sequential batch learning problem in linear contextual bandits with finite action sets, where the decision maker is constrained to split incoming individuals into (at most) a fixed number of batches and can only observe outcomes for the individuals within a batch at the batch's end.

By Yanjun Han, Zhengqing Zhou, Zihao Hu, Jose Blanchet, Peter W. Glynn, Yinyu Ye, Zhengyuan Zhou

reinforcement-learning

arXiv AI

Jun 15

Learning optimal policies from event logs through reinforcement learning: a comparison of deep and MDP-based approaches

arXiv:2303. 09209v2 Announce Type: replace Abstract: Prescriptive Process Monitoring is an emerging area within Process Mining that focuses on recommending actions to optimize business outcomes.

By Stefano Branchi, Andrei Buliga, Chiara Di Francescomarino, Chiara Ghidini, Riccardo Graziosi, Francesca Meneghello, Massimiliano Ronzani

reinforcement-learning benchmarks

arXiv AI

Jul 14

Training on Irrelevant States Implies Data Augmentation: Generalization in Contextual MDPs

arXiv:2410. 03565v4 Announce Type: replace-cross Abstract: In the zero-shot policy transfer (ZSPT) setting for contextual Markov decision processes (CMDP), agents train on a fixed, finite set of contexts and must generalize to new ones.

By Max Weltevrede, Caroline Horsch, Matthijs T. J. Spaan, Wendelin B\"ohmer

agents reinforcement-learning benchmarks

arXiv Machine Learning

Jun 9

CAAL: Contextual Bandits based Online Hand-Craft Active Learning Strategy Selection

arXiv:2606. 07910v1 Announce Type: new Abstract: The challenge with active learning algorithms is the uncertainty of the statistical distribution of unlabeled data, making it difficult to choose the best hand-crafted strategy.

By Shao-An Yin, Jiacong Li, Tianpei Xie, Cecile Levasseur, Wojciech Kowalinski, Nicola Elia

Related stories

Off-Policy Learning in Large Action Spaces: Optimization Matters More Than Estimation

On-Policy and Off-Policy Learning for Large Action Spaces

Sequential Batch Learning in Finite-Action Linear Contextual Bandits

Learning optimal policies from event logs through reinforcement learning: a comparison of deep and MDP-based approaches

Training on Irrelevant States Implies Data Augmentation: Generalization in Contextual MDPs

CAAL: Contextual Bandits based Online Hand-Craft Active Learning Strategy Selection