{"total":12,"rows":[{"id":"2210.13132","title":"PAC-Bayesian Offline Contextual Bandits With Guarantees","created":"2022-10-24","cited_by_count":20,"area":null},{"id":"2309.11518","title":"Ad-load Balancing via Off-policy Learning in a Content Marketplace","created":"2023-09-19","cited_by_count":12,"area":null},{"id":"2212.11431","title":"Local Policy Improvement for Recommender Systems","created":"2022-12-22","cited_by_count":9,"area":null},{"id":"2404.15084","title":"Hyperparameter Optimization Can Even be Harmful in Off-Policy Learning and How to Deal with It","created":"2024-04-23","cited_by_count":5,"area":null},{"id":"2208.01148","title":"Boosted Off-Policy Learning","created":"2022-08-01","cited_by_count":3,"area":null},{"id":"2509.05460","title":"Calibrated Recommendations with Contextual Bandits","created":"2025-09-05","cited_by_count":3,"area":null},{"id":"2206.02593","title":"Pessimistic Off-Policy Optimization for Learning to Rank","created":"2022-06-06","cited_by_count":2,"area":null},{"id":"2202.13337","title":"Towards Robust Off-policy Learning for Runtime Uncertainty","created":"2022-02-27","cited_by_count":1,"area":null},{"id":"2510.07635","title":"Safely Exploring Novel Actions in Recommender Systems via Deployment-Efficient Policy Learning","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2606.07399","title":"Are Good Generators Good Decision-Makers? Policy Learning for General Interventions via Retargeted Counterfactual Generation","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2609.36740","title":"Efficient Offline Learning of Ranking Policies via Top-$k$ Policy Decomposition","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00729","title":"Reward as Observation: Learning Reward-Based Policies for Rapid Adaptation","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}