{"total":23,"rows":[{"id":"2104.12820","title":"Universal Off-Policy Evaluation","created":"2021-04-26","cited_by_count":43,"area":null},{"id":"2104.08977","title":"Off-Policy Risk Assessment in Contextual Bandits","created":"2021-04-18","cited_by_count":29,"area":null},{"id":"2102.08492","title":"Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments","created":"2021-02-16","cited_by_count":26,"area":null},{"id":"2206.04405","title":"Conformal Off-Policy Prediction in Contextual Bandits","created":"2022-06-09","cited_by_count":25,"area":null},{"id":"2111.12482","title":"One More Step Towards Reality: Cooperative Bandits with Imperfect Communication","created":"2021-11-24","cited_by_count":15,"area":null},{"id":"2205.14174","title":"Private and Byzantine-Proof Cooperative Decision-Making","created":"2022-05-27","cited_by_count":10,"area":null},{"id":"2102.05018","title":"Robust Bandit Learning with Imperfect Context","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2208.11744","title":"Enforcing Delayed-Impact Fairness Guarantees","created":"2022-08-24","cited_by_count":8,"area":null},{"id":"2102.12722","title":"Combinatorial Bandits under Strategic Manipulations","created":"2021-02-25","cited_by_count":6,"area":null},{"id":"2111.07458","title":"Mean-based Best Arm Identification in Stochastic Bandits under Reward Contamination","created":"2021-11-14","cited_by_count":6,"area":null},{"id":"2205.04134","title":"Federated Multi-Armed Bandits Under Byzantine Attacks","created":"2022-05-09","cited_by_count":6,"area":null},{"id":"2301.12595","title":"Adversarial Attacks on Adversarial Bandits","created":"2023-01-30","cited_by_count":6,"area":null},{"id":"2209.03540","title":"Reward Delay Attacks on Deep Reinforcement Learning","created":"2022-09-08","cited_by_count":5,"area":null},{"id":"2301.09024","title":"Statistically Optimal Robust Mean and Covariance Estimation for Anisotropic Gaussians","created":"2023-01-21","cited_by_count":3,"area":null},{"id":"2305.12283","title":"Distribution-Free Model-Agnostic Regression Calibration via Nonparametric Methods","created":"2023-05-20","cited_by_count":3,"area":null},{"id":"2310.15932","title":"Online Robust Mean Estimation","created":"2023-10-24","cited_by_count":3,"area":null},{"id":"2308.14165","title":"Distributional Off-Policy Evaluation for Slate Recommendations","created":"2023-08-27","cited_by_count":2,"area":null},{"id":"2309.16563","title":"CRIMED: Lower and Upper Bounds on Regret for Bandits with Unbounded Stochastic Corruption","created":"2023-09-28","cited_by_count":2,"area":null},{"id":"2210.13692","title":"Sequential Decision Making on Unmatched Data using Bayesian Kernel Embeddings","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2408.12581","title":"Identifying the Best Arm in the Presence of Global Environment Shifts","created":"2024-08-22","cited_by_count":1,"area":null},{"id":"2604.14860","title":"Best of both worlds: Stochastic & adversarial best-arm identification","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2206.02666","title":"Robust Pareto Set Identification with Contaminated Bandit Feedback","created":"2022-06-06","cited_by_count":0,"area":null},{"id":"2610.17760","title":"Gaussian Process Bandits for AI System Optimization with Selectively Verified Feedback","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}