{"total":26,"rows":[{"id":"2112.00885","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning","created":"2021-12-01","cited_by_count":35,"area":null},{"id":"2102.05295","title":"An Efficient Pessimistic-Optimistic Algorithm for Stochastic Linear Bandits with General Constraints","created":"2021-02-10","cited_by_count":29,"area":null},{"id":"2111.12151","title":"Best Arm Identification with Safety Constraints","created":"2021-11-23","cited_by_count":25,"area":null},{"id":"2206.11183","title":"Active Learning with Safety Constraints","created":"2022-06-22","cited_by_count":16,"area":null},{"id":"2202.13234","title":"Safe Exploration for Efficient Policy Evaluation and Comparison","created":"2022-02-26","cited_by_count":15,"area":null},{"id":"2102.10156","title":"Learning to Persuade on the Fly: Robustness Against Ignorance","created":"2021-02-19","cited_by_count":12,"area":null},{"id":"2106.11512","title":"An Accurate Non-accelerometer-based PPG Motion Artifact Removal Technique using CycleGAN","created":"2021-06-22","cited_by_count":10,"area":null},{"id":"2308.15006","title":"Directional Optimism for Safe Linear Bandits","created":"2023-08-29","cited_by_count":8,"area":null},{"id":"2106.05378","title":"Feature and Parameter Selection in Stochastic Linear Bandits","created":"2021-06-09","cited_by_count":5,"area":null},{"id":"2311.04338","title":"Convex Methods for Constrained Linear Bandits","created":"2023-11-07","cited_by_count":5,"area":null},{"id":"2205.06326","title":"Multi-Environment Meta-Learning in Stochastic Linear Bandits","created":"2022-05-12","cited_by_count":4,"area":null},{"id":"2205.06331","title":"Collaborative Multi-agent Stochastic Linear Bandits","created":"2022-05-12","cited_by_count":4,"area":null},{"id":"2201.07139","title":"Safe Online Bid Optimization with Return on Investment and Budget Constraints","created":"2022-01-18","cited_by_count":3,"area":null},{"id":"2305.00889","title":"The Impact of the Geometric Properties of the Constraint Set in Safe Optimization with Bandit Feedback","created":"2023-05-01","cited_by_count":3,"area":null},{"id":"2102.01749","title":"Vehicle trajectory prediction in top-view image sequences based on deep learning method","created":"2021-02-02","cited_by_count":2,"area":null},{"id":"2105.08748","title":"Learning to Act Safely with Limited Exposure and Almost Sure Certainty","created":"2021-05-18","cited_by_count":2,"area":null},{"id":"2205.13689","title":"Safety Aware Changepoint Detection for Piecewise i.i.d. Bandits","created":"2022-05-27","cited_by_count":2,"area":null},{"id":"2302.13252","title":"No-Regret Linear Bandits beyond Realizability","created":"2023-02-26","cited_by_count":2,"area":null},{"id":"2401.11563","title":"Distributed Multi-Task Learning for Stochastic Bandits with Context Distribution and Stage-wise Constraints","created":"2024-01-21","cited_by_count":2,"area":null},{"id":"2301.13393","title":"Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits","created":"2023-01-31","cited_by_count":1,"area":null},{"id":"2505.02640","title":"Adaptive Budgeted Multi-Armed Bandits for IoT with Dynamic Resource Constraints","created":"2025-05-05","cited_by_count":1,"area":null},{"id":"2510.00602","title":"Multi-Agent Stage-wise Conservative Linear Bandits","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2305.01202","title":"Exploration of Unranked Items in Safe Online Learning to Re-Rank","created":"2023-05-02","cited_by_count":0,"area":null},{"id":"2501.18560","title":"Bandits with Anytime Knapsacks","created":"2025-01-30","cited_by_count":0,"area":null},{"id":"2605.12176","title":"Multi-Task Representation Learning for Conservative Linear Bandits","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2610.01377","title":"Minimax Optimal Regret for Causal Logistic Bandits with Counterfactual Fairness","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}