{"total":19,"rows":[{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166,"area":null},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2106.06239","title":"Safe Reinforcement Learning with Linear Function Approximation","created":"2021-06-11","cited_by_count":35,"area":null},{"id":"2104.14527","title":"Online certification of preference-based fairness for personalized recommender systems","created":"2021-04-29","cited_by_count":22,"area":null},{"id":"2108.04782","title":"Bandit Algorithms for Precision Medicine","created":"2021-08-10","cited_by_count":12,"area":null},{"id":"2206.14057","title":"Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-free RL","created":"2022-06-28","cited_by_count":10,"area":null},{"id":"2106.11692","title":"A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning","created":"2021-06-22","cited_by_count":9,"area":null},{"id":"2111.07395","title":"Explicit Explore, Exploit, or Escape ($E^4$): near-optimal safety-constrained reinforcement learning in polynomial time","created":"2021-11-14","cited_by_count":6,"area":null},{"id":"2306.00172","title":"Learning for Edge-Weighted Online Bipartite Matching with Robustness Guarantees","created":"2023-05-31","cited_by_count":5,"area":null},{"id":"2306.06265","title":"Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise Constraints","created":"2023-06-09","cited_by_count":5,"area":null},{"id":"2110.13060","title":"Uniformly Conservative Exploration in Reinforcement Learning","created":"2021-10-25","cited_by_count":3,"area":null},{"id":"2502.11673","title":"Best of Both Worlds: Regret Minimization versus Minimax Play","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2306.10158","title":"Learning-Augmented Decentralized Online Convex Optimization in Networks","created":"2023-06-16","cited_by_count":1,"area":null},{"id":"2311.01568","title":"Anytime-Competitive Reinforcement Learning with Policy Prior","created":"2023-11-02","cited_by_count":1,"area":null},{"id":"2103.03307","title":"Conservative Optimistic Policy Optimization via Multiple Importance Sampling","created":"2021-03-04","cited_by_count":0,"area":null},{"id":"2302.03784","title":"Leveraging User-Triggered Supervision in Contextual Bandits","created":"2023-02-07","cited_by_count":0,"area":null},{"id":"2312.15458","title":"Conservative Exploration for Policy Optimization via Off-Policy Policy Evaluation","created":"2023-12-24","cited_by_count":0,"area":null},{"id":"2603.22348","title":"Learning Safely Without Knowing the World:COMPASS-Hedge","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2607.29400","title":"ALIVE: Warnings Before Exclusion in Budgeted Multi-Source Learning","created":"2026-07-31","cited_by_count":0,"area":null}],"next_cursor":null}