{"total":310,"rows":[{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"area":null},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328,"area":"alignment"},{"id":"2408.03539","title":"Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes","created":"2024-08-07","cited_by_count":176,"area":"deeprl"},{"id":"2202.11566","title":"Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning","created":"2022-02-23","cited_by_count":125,"area":"offlinerl"},{"id":"2106.10783","title":"OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation","created":"2021-06-21","cited_by_count":121,"area":"offlinerl"},{"id":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116,"area":null},{"id":"2103.05577","title":"Parametrized quantum policies for reinforcement learning","created":"2021-03-09","cited_by_count":90,"area":null},{"id":"2107.11003","title":"Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings","created":"2021-07-23","cited_by_count":68,"area":"offlinerl"},{"id":"2303.11568","title":"Large AI Models in Health Informatics: Applications, Challenges, and the Future","created":"2023-03-21","cited_by_count":61,"area":null},{"id":"2409.00265","title":"Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction","created":"2024-08-30","cited_by_count":46,"area":null},{"id":"2302.05209","title":"A Survey on Causal Reinforcement Learning","created":"2023-02-10","cited_by_count":45,"area":null},{"id":"2402.02025","title":"A Survey of Constraint Formulations in Safe Reinforcement Learning","created":"2024-02-03","cited_by_count":44,"area":"deeprl"},{"id":"2302.11312","title":"Behavior Proximal Policy Optimization","created":"2023-02-22","cited_by_count":43,"area":"offlinerl"},{"id":"2210.01808","title":"Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees","created":"2022-10-04","cited_by_count":42,"area":"offlinerl"},{"id":"2211.04974","title":"Leveraging Offline Data in Online Reinforcement Learning","created":"2022-11-09","cited_by_count":42,"area":"offlinerl"},{"id":"2106.04152","title":"PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning","created":"2021-06-08","cited_by_count":41,"area":null},{"id":"2502.13187","title":"A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models","created":"2025-02-18","cited_by_count":38,"area":"deeprl"},{"id":"2209.08025","title":"Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability","created":"2022-09-16","cited_by_count":36,"area":null},{"id":"2505.05108","title":"Multi-agent Embodied AI: Advances and Future Directions","created":"2025-05-08","cited_by_count":36,"area":null},{"id":"2007.01174","title":"Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch","created":"2020-07-02","cited_by_count":33,"area":"offlinerl"},{"id":"2202.06385","title":"Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost","created":"2022-02-13","cited_by_count":32,"area":null},{"id":"2209.06620","title":"Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation","created":"2022-09-14","cited_by_count":32,"area":"offlinerl"},{"id":"2204.12993","title":"Counterfactual harm","created":"2022-04-27","cited_by_count":29,"area":null},{"id":"2210.07573","title":"Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm","created":"2022-10-14","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":"2207.14800","title":"Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning","created":"2022-07-29","cited_by_count":26,"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":"2211.12612","title":"Transfer Learning for Contextual Multi-armed Bandits","created":"2022-11-22","cited_by_count":24,"area":null},{"id":"2309.01038","title":"Neurosymbolic Reinforcement Learning and Planning: A Survey","created":"2023-09-02","cited_by_count":24,"area":null},{"id":"2210.06692","title":"Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief","created":"2022-10-13","cited_by_count":22,"area":"offlinerl"},{"id":"2302.10261","title":"Deep Reinforcement Learning for Cost-Effective Medical Diagnosis","created":"2023-02-20","cited_by_count":21,"area":null},{"id":"2305.19562","title":"Replicability in Reinforcement Learning","created":"2023-05-31","cited_by_count":21,"area":null},{"id":"2206.12984","title":"Improving Policy Optimization with Generalist-Specialist Learning","created":"2022-06-26","cited_by_count":20,"area":null},{"id":"2305.18427","title":"Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach","created":"2023-05-28","cited_by_count":19,"area":null},{"id":"2101.00135","title":"Faults in Deep Reinforcement Learning Programs: A Taxonomy and A Detection Approach","created":"2021-01-01","cited_by_count":18,"area":null},{"id":"2203.09365","title":"Semi-Markov Offline Reinforcement Learning for Healthcare","created":"2022-03-17","cited_by_count":18,"area":"offlinerl"},{"id":"2208.14226","title":"Unsupervised Representation Learning in Deep Reinforcement Learning: A Review","created":"2022-08-27","cited_by_count":18,"area":null},{"id":"2106.01577","title":"A Provably-Efficient Model-Free Algorithm for Constrained Markov Decision Processes","created":"2021-06-03","cited_by_count":17,"area":null},{"id":"2302.07549","title":"Deep Offline Reinforcement Learning for Real-world Treatment Optimization Applications","created":"2023-02-15","cited_by_count":17,"area":"offlinerl"},{"id":"2302.12689","title":"GANterfactual-RL: Understanding Reinforcement Learning Agents' Strategies through Visual Counterfactual Explanations","created":"2023-02-24","cited_by_count":17,"area":null},{"id":"2101.08477","title":"Unifying Cardiovascular Modelling with Deep Reinforcement Learning for Uncertainty Aware Control of Sepsis Treatment","created":"2021-01-21","cited_by_count":16,"area":null},{"id":"2106.05012","title":"Bayesian Bellman Operators","created":"2021-06-09","cited_by_count":16,"area":null},{"id":"2210.02552","title":"Towards Safe Mechanical Ventilation Treatment Using Deep Offline Reinforcement Learning","created":"2022-10-05","cited_by_count":16,"area":"offlinerl"},{"id":"2307.11352","title":"Model-based Offline Reinforcement Learning with Count-based Conservatism","created":"2023-07-21","cited_by_count":16,"area":"offlinerl"},{"id":"2402.01874","title":"The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2301.10009","title":"Remote patient monitoring using artificial intelligence: Current state, applications, and challenges","created":"2023-01-19","cited_by_count":14,"area":null},{"id":"2403.12946","title":"Sample Complexity of Offline Distributionally Robust Linear Markov Decision Processes","created":"2024-03-19","cited_by_count":14,"area":"offlinerl"},{"id":"2404.14942","title":"Manipulating Recommender Systems: A Survey of Poisoning Attacks and Countermeasures","created":"2024-04-23","cited_by_count":14,"area":null},{"id":"2110.13052","title":"Can Q-Learning be Improved with Advice?","created":"2021-10-25","cited_by_count":13,"area":null},{"id":"2210.00701","title":"Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation","created":"2022-10-03","cited_by_count":13,"area":null},{"id":"2306.03929","title":"Finding Counterfactually Optimal Action Sequences in Continuous State Spaces","created":"2023-06-06","cited_by_count":13,"area":null},{"id":"2311.14168","title":"Fast Policy Learning for Linear Quadratic Control with Entropy Regularization","created":"2023-11-23","cited_by_count":13,"area":null},{"id":"2403.03811","title":"Incentivized Learning in Principal-Agent Bandit Games","created":"2024-03-06","cited_by_count":13,"area":null},{"id":"2112.00733","title":"Efficient Symptom Inquiring and Diagnosis via Adaptive Alignment of Reinforcement Learning and Classification","created":"2021-12-01","cited_by_count":12,"area":null},{"id":"2210.01282","title":"Structural Estimation of Markov Decision Processes in High-Dimensional State Space with Finite-Time Guarantees","created":"2022-10-04","cited_by_count":12,"area":"offlinerl"},{"id":"2301.11147","title":"Train Hard, Fight Easy: Robust Meta Reinforcement Learning","created":"2023-01-26","cited_by_count":12,"area":null},{"id":"2303.14716","title":"Balancing policy constraint and ensemble size in uncertainty-based offline reinforcement learning","created":"2023-03-26","cited_by_count":12,"area":"offlinerl"},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2511.20766","title":"OpenApps: Simulating Environment Variations to Measure UI-Agent Reliability","created":"2025-11-25","cited_by_count":12,"area":null},{"id":"2307.04354","title":"Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data","created":"2023-07-10","cited_by_count":11,"area":null},{"id":"2311.02129","title":"Hierarchical Reinforcement Learning for Power Network Topology Control","created":"2023-11-03","cited_by_count":11,"area":null},{"id":"2108.04526","title":"A Survey on Deep Reinforcement Learning for Data Processing and Analytics","created":"2021-08-10","cited_by_count":10,"area":null},{"id":"2201.12594","title":"Robust Imitation Learning from Corrupted Demonstrations","created":"2022-01-29","cited_by_count":10,"area":"offlinerl"},{"id":"2205.03755","title":"DxFormer: A Decoupled Automatic Diagnostic System Based on Decoder-Encoder Transformer with Dense Symptom Representations","created":"2022-05-08","cited_by_count":10,"area":null},{"id":"2210.13623","title":"Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2303.08271","title":"Act-Then-Measure: Reinforcement Learning for Partially Observable Environments with Active Measuring","created":"2023-03-14","cited_by_count":10,"area":null},{"id":"2402.06819","title":"Monitored Markov Decision Processes","created":"2024-02-09","cited_by_count":10,"area":"deeprl"},{"id":"2409.07569","title":"A Comprehensive Survey on Inverse Constrained Reinforcement Learning: Definitions, Progress and Challenges","created":"2024-09-11","cited_by_count":10,"area":"deeprl"},{"id":"2409.10277","title":"Cognitive Kernel: An Open-source Agent System towards Generalist Autopilots","created":"2024-09-16","cited_by_count":10,"area":"agents"},{"id":"2510.04587","title":"Pathology-CoT: Learning Visual Chain-of-Thought Agent from Expert Whole Slide Image Diagnosis Behavior","created":"2025-10-06","cited_by_count":10,"area":"lr"},{"id":"2204.12561","title":"Learning Eco-Driving Strategies at Signalized Intersections","created":"2022-04-26","cited_by_count":9,"area":"driving"},{"id":"2206.11996","title":"The Real Deal: A Review of Challenges and Opportunities in Moving Reinforcement Learning-Based Traffic Signal Control Systems Towards Reality","created":"2022-06-23","cited_by_count":9,"area":null},{"id":"2302.12456","title":"Logarithmic Switching Cost in Reinforcement Learning beyond Linear MDPs","created":"2023-02-24","cited_by_count":9,"area":null},{"id":"2308.02877","title":"Meta-learning in healthcare: A survey","created":"2023-08-05","cited_by_count":9,"area":null},{"id":"2312.03991","title":"MICRO: Model-Based Offline Reinforcement Learning with a Conservative Bellman Operator","created":"2023-12-07","cited_by_count":9,"area":"offlinerl"},{"id":"2411.05234","title":"Performative Reinforcement Learning with Linear Markov Decision Process","created":"2024-11-07","cited_by_count":9,"area":"deeprl"},{"id":"2505.19785","title":"medDreamer: Model-Based Reinforcement Learning with Latent Imagination on Complex EHRs for Clinical Decision Support","created":"2025-05-26","cited_by_count":9,"area":"deeprl"},{"id":"2505.23062","title":"Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics Data","created":"2025-05-29","cited_by_count":9,"area":"diffusion"},{"id":"2102.06779","title":"Machine Learning for Mechanical Ventilation Control","created":"2021-02-12","cited_by_count":8,"area":null},{"id":"2405.01327","title":"Constrained Reinforcement Learning Under Model Mismatch","created":"2024-05-02","cited_by_count":8,"area":"deeprl"},{"id":"2405.18610","title":"DTR-Bench: An in silico Environment and Benchmark Platform for Reinforcement Learning Based Dynamic Treatment Regime","created":"2024-05-28","cited_by_count":8,"area":"deeprl"},{"id":"2406.12550","title":"Offline Imitation Learning with Model-based Reverse Augmentation","created":"2024-06-18","cited_by_count":8,"area":"offlinerl"},{"id":"2408.11943","title":"Advances in Preference-based Reinforcement Learning: A Review","created":"2024-08-21","cited_by_count":8,"area":"deeprl"},{"id":"2411.00465","title":"Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions","created":"2024-11-01","cited_by_count":8,"area":"offlinerl"},{"id":"2210.10464","title":"On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness","created":"2022-10-19","cited_by_count":7,"area":null},{"id":"2301.00188","title":"New Challenges in Reinforcement Learning: A Survey of Security and Privacy","created":"2022-12-31","cited_by_count":7,"area":null},{"id":"2301.08940","title":"Quasi-optimal Reinforcement Learning with Continuous Actions","created":"2023-01-21","cited_by_count":7,"area":null},{"id":"2305.05586","title":"RLocator: Reinforcement Learning for Bug Localization","created":"2023-05-09","cited_by_count":7,"area":null},{"id":"2305.12569","title":"Conditional Generative Modeling for High-dimensional Marked Temporal Point Processes","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2310.17146","title":"Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2404.19346","title":"Pessimistic Value Iteration for Multi-Task Data Sharing in Offline Reinforcement Learning","created":"2024-04-30","cited_by_count":7,"area":"offlinerl"},{"id":"2502.16816","title":"Finite-Sample Analysis of Policy Evaluation for Robust Average Reward Reinforcement Learning","created":"2025-02-24","cited_by_count":7,"area":"deeprl"},{"id":"2112.02215","title":"Deep Policy Iteration with Integer Programming for Inventory Management","created":"2021-12-04","cited_by_count":6,"area":null},{"id":"2201.03698","title":"Verified Probabilistic Policies for Deep Reinforcement Learning","created":"2022-01-10","cited_by_count":6,"area":null},{"id":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2203.02605","title":"Reinforcement Learning in Modern Biostatistics: Constructing Optimal Adaptive Interventions","created":"2022-03-04","cited_by_count":6,"area":null},{"id":"2209.09023","title":"Artificial Intelligence for In Silico Clinical Trials: A Review","created":"2022-09-16","cited_by_count":6,"area":null},{"id":"2301.05664","title":"Risk Sensitive Dead-end Identification in Safety-Critical Offline Reinforcement Learning","created":"2023-01-13","cited_by_count":6,"area":"offlinerl"},{"id":"2310.01706","title":"On Representation Complexity of Model-based and Model-free Reinforcement Learning","created":"2023-10-03","cited_by_count":6,"area":null},{"id":"2403.09940","title":"Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries","created":"2024-03-15","cited_by_count":6,"area":"deeprl"}],"next_cursor":"100"}