{"total":43,"rows":[{"id":"2306.02451","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","created":"2023-06-04","cited_by_count":75,"area":null},{"id":"2204.08957","title":"COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation","created":"2022-04-19","cited_by_count":71,"area":null},{"id":"2207.00429","title":"Modular Lifelong Reinforcement Learning via Neural Composition","created":"2022-07-01","cited_by_count":40,"area":null},{"id":"2305.00567","title":"Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RL","created":"2023-04-30","cited_by_count":36,"area":null},{"id":"2211.11349","title":"Data-Driven Offline Decision-Making via Invariant Representation Learning","created":"2022-11-21","cited_by_count":31,"area":null},{"id":"2210.07006","title":"Sustainable Online Reinforcement Learning for Auto-bidding","created":"2022-10-13","cited_by_count":29,"area":null},{"id":"2110.04186","title":"Medical Dead-ends and Learning to Identify High-risk States and Treatments","created":"2021-10-08","cited_by_count":28,"area":null},{"id":"2206.10524","title":"Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control","created":"2022-06-21","cited_by_count":28,"area":null},{"id":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24,"area":null},{"id":"2202.13536","title":"LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimation","created":"2022-02-28","cited_by_count":23,"area":null},{"id":"2301.04939","title":"Safe Policy Improvement for POMDPs via Finite-State Controllers","created":"2023-01-12","cited_by_count":12,"area":null},{"id":"2303.05848","title":"Decision-Making Under Uncertainty: Beyond Probabilities","created":"2023-03-10","cited_by_count":9,"area":null},{"id":"2502.13022","title":"Efficient and Sharp Off-Policy Learning under Unobserved Confounding","created":"2025-02-18","cited_by_count":6,"area":null},{"id":"2109.14727","title":"Dr Jekyll and Mr Hyde: the Strange Case of Off-Policy Policy Updates","created":"2021-09-29","cited_by_count":5,"area":null},{"id":"2201.12175","title":"Safe Policy Improvement Approaches on Discrete Markov Decision Processes","created":"2022-01-28","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":"2111.04835","title":"Safe Data Collection for Offline and Online Policy Learning","created":"2021-11-08","cited_by_count":4,"area":null},{"id":"2403.07933","title":"Corruption-Robust Offline Two-Player Zero-Sum Markov Games","created":"2024-03-04","cited_by_count":4,"area":null},{"id":"2209.09446","title":"A Joint Imitation-Reinforcement Learning Framework for Reduced Baseline Regret","created":"2022-09-20","cited_by_count":3,"area":null},{"id":"2308.11267","title":"Robust Lagrangian and Adversarial Policy Gradient for Robust Constrained Markov Decision Processes","created":"2023-08-22","cited_by_count":3,"area":null},{"id":"2609.22819","title":"Counterfactual Tool Ranking under Utility, Cost, and Privilege Constraints","created":"2026-09-19","cited_by_count":3,"area":null},{"id":"2106.00589","title":"Improving Long-Term Metrics in Recommendation Systems using Short-Horizon Reinforcement Learning","created":"2021-06-01","cited_by_count":2,"area":null},{"id":"2106.09973","title":"The Curse of Passive Data Collection in Batch Reinforcement Learning","created":"2021-06-18","cited_by_count":2,"area":null},{"id":"2202.07496","title":"Beyond the Policy Gradient Theorem for Efficient Policy Updates in Actor-Critic Algorithms","created":"2022-02-15","cited_by_count":2,"area":null},{"id":"2209.04265","title":"Route Planning for Last-Mile Deliveries Using Mobile Parcel Lockers: A Hybrid Q-Learning Network Approach","created":"2022-09-09","cited_by_count":2,"area":null},{"id":"2303.11187","title":"A Unified Framework of Policy Learning for Contextual Bandit with Confounding Bias and Missing Observations","created":"2023-03-20","cited_by_count":2,"area":null},{"id":"2408.12004","title":"CSPI-MT: Calibrated Safe Policy Improvement with Multiple Testing for Threshold Policies","created":"2024-08-21","cited_by_count":2,"area":null},{"id":"2506.08062","title":"FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2109.09034","title":"Greedy UnMixing for Q-Learning in Multi-Agent Reinforcement Learning","created":"2021-09-19","cited_by_count":1,"area":null},{"id":"2407.13006","title":"Sparsity-based Safety Conservatism for Constrained Offline Reinforcement Learning","created":"2024-07-17","cited_by_count":1,"area":null},{"id":"2506.08644","title":"Semi-gradient DICE for Offline Constrained Reinforcement Learning","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2110.15485","title":"Location-routing Optimisation for Urban Logistics Using Mobile Parcel Locker Based on Hybrid Q-Learning Algorithm","created":"2021-10-29","cited_by_count":0,"area":null},{"id":"2205.13950","title":"Non-Markovian policies occupancy measures","created":"2022-05-27","cited_by_count":0,"area":null},{"id":"2302.03586","title":"Adaptive Aggregation for Safety-Critical Control","created":"2023-02-07","cited_by_count":0,"area":null},{"id":"2312.00727","title":"Safe Reinforcement Learning in Tensor Reproducing Kernel Hilbert Space","created":"2023-12-01","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":"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":"2510.19672","title":"Policy Learning with Abstention","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2605.29788","title":"Certified Policy Optimisation for Nested Causal Bandits via PAC-Bayes Risk","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2609.20304","title":"Diagnose, Recover, Certify: Task Readiness under Hidden Dynamics Changes","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2609.33669","title":"RSD-Poker: Structure-Adaptive and Shift-Robust Risk-Utility Certification for Residual Policies in Imperfect-Information Games","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.36614","title":"Selective Elicitation as a Commercial Influence Channel: A Reproducible Synthetic Shopping-Agent Stress Test","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.20473","title":"SafeAdapt-Poker: Counterfactual Risk Calibration for Budgeted Adaptation under Opponent Shift","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}