{"total":33,"rows":[{"id":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141,"area":null},{"id":"2303.06614","title":"Synthetic Experience Replay","created":"2023-03-12","cited_by_count":101,"area":null},{"id":"2208.09052","title":"A Review of Uncertainty for Deep Reinforcement Learning","created":"2022-08-18","cited_by_count":40,"area":null},{"id":"2211.07357","title":"Controlling Commercial Cooling Systems Using Reinforcement Learning","created":"2022-11-11","cited_by_count":29,"area":null},{"id":"2303.02618","title":"Ensemble Reinforcement Learning: A Survey","created":"2023-03-05","cited_by_count":16,"area":null},{"id":"2302.12526","title":"Model-Based Uncertainty in Value Functions","created":"2023-02-24","cited_by_count":15,"area":null},{"id":"2306.06335","title":"How to Learn and Generalize From Three Minutes of Data: Physics-Constrained and Uncertainty-Aware Neural Stochastic Differential Equations","created":"2023-06-10","cited_by_count":10,"area":null},{"id":"2201.13357","title":"DNS: Determinantal Point Process Based Neural Network Sampler for Ensemble Reinforcement Learning","created":"2022-01-31","cited_by_count":8,"area":null},{"id":"2401.03137","title":"SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning","created":"2024-01-06","cited_by_count":8,"area":null},{"id":"2508.04780","title":"Uncertainty-aware Predict-Then-Optimize Framework for Equitable Post-Disaster Power Restoration","created":"2025-08-06","cited_by_count":7,"area":null},{"id":"2312.10289","title":"Active Reinforcement Learning for Robust Building Control","created":"2023-12-16","cited_by_count":4,"area":null},{"id":"2504.13368","title":"An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2303.06389","title":"Uncertainty-Aware Instance Reweighting for Off-Policy Learning","created":"2023-03-11","cited_by_count":3,"area":null},{"id":"2312.04386","title":"Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2411.04138","title":"NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2605.05857","title":"Offline Reinforcement Learning for Rotation Profile Control in Tokamaks","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2209.14488","title":"Ensemble Reinforcement Learning in Continuous Spaces -- A Hierarchical Multi-Step Approach for Policy Training","created":"2022-09-29","cited_by_count":1,"area":null},{"id":"2305.11616","title":"Diversifying Deep Ensembles: A Saliency Map Approach for Enhanced OOD Detection, Calibration, and Accuracy","created":"2023-05-19","cited_by_count":1,"area":null},{"id":"2311.02787","title":"Make a Donut: Hierarchical EMD-Space Planning for Zero-Shot Deformable Manipulation with Tools","created":"2023-11-05","cited_by_count":1,"area":null},{"id":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2602.05776","title":"Cross-Domain Offline Policy Adaptation via Selective Transition Correction","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2605.27877","title":"SPAR: Support-Preserving Action Rectification","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2210.13545","title":"MEET: A Monte Carlo Exploration-Exploitation Trade-off for Buffer Sampling","created":"2022-10-24","cited_by_count":0,"area":null},{"id":"2304.00573","title":"Risk-Sensitive and Robust Model-Based Reinforcement Learning and Planning","created":"2023-04-02","cited_by_count":0,"area":null},{"id":"2308.01759","title":"Bag of Policies for Distributional Deep Exploration","created":"2023-08-03","cited_by_count":0,"area":null},{"id":"2401.05341","title":"Stable Online and Offline Reinforcement Learning for Antibody CDRH3 Design","created":"2023-11-29","cited_by_count":0,"area":null},{"id":"2406.02456","title":"Offline Bayesian Aleatoric and Epistemic Uncertainty Quantification and Posterior Value Optimisation in Finite-State MDPs","created":"2024-06-04","cited_by_count":0,"area":null},{"id":"2505.00913","title":"Fine-Tuning without Performance Degradation","created":"2025-05-01","cited_by_count":0,"area":null},{"id":"2505.00961","title":"DOLCE: Decomposing Off-Policy Evaluation/Learning into Lagged and Current Effects","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2505.12759","title":"Your Offline Policy is Not Trustworthy: Bilevel Reinforcement Learning for Sequential Portfolio Optimization","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2510.27114","title":"Learning Robust Visuomotor Policies via Dynamics Alignment","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2602.22226","title":"SEGB: Self-Evolved Generative Bidding with Local Autoregressive Diffusion","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2607.26599","title":"Uncertainty-Guided LLM Semantic Augmentation for Heterogeneous Treatment Effect Estimation","created":"2026-07-29","cited_by_count":0,"area":null}],"next_cursor":null}