{"total":165,"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":"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":"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":"2106.04152","title":"PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning","created":"2021-06-08","cited_by_count":41,"area":null},{"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":"2202.06385","title":"Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost","created":"2022-02-13","cited_by_count":32,"area":null},{"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":"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":"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":"2302.12689","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":"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":"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":"2301.11147","title":"Train Hard, Fight Easy: Robust Meta Reinforcement Learning","created":"2023-01-26","cited_by_count":12,"area":null},{"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":"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":"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":"2102.06779","title":"Machine Learning for Mechanical Ventilation Control","created":"2021-02-12","cited_by_count":8,"area":null},{"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":"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":"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":"2110.07510","title":"Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning","created":"2021-10-14","cited_by_count":5,"area":null},{"id":"2111.00185","title":"Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings","created":"2021-10-30","cited_by_count":5,"area":null},{"id":"2211.05551","title":"Causal Counterfactuals for Improving the Robustness of Reinforcement Learning","created":"2022-11-02","cited_by_count":5,"area":null},{"id":"2211.07092","title":"Offline Estimation of Controlled Markov Chains: Minimaxity and Sample Complexity","created":"2022-11-14","cited_by_count":5,"area":null},{"id":"2304.10000","title":"Model Based Reinforcement Learning for Personalized Heparin Dosing","created":"2023-04-19","cited_by_count":5,"area":null},{"id":"2304.12090","title":"Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Survey","created":"2023-04-24","cited_by_count":5,"area":null},{"id":"2309.09457","title":"Exploring and Learning in Sparse Linear MDPs without Computationally Intractable Oracles","created":"2023-09-18","cited_by_count":5,"area":null},{"id":"2311.17165","title":"(Ir)rationality in AI: State of the Art, Research Challenges and Open Questions","created":"2023-11-28","cited_by_count":5,"area":null},{"id":"2109.07171","title":"Balancing detectability and performance of attacks on the control channel of Markov Decision Processes","created":"2021-09-15","cited_by_count":4,"area":null},{"id":"2202.03486","title":"Optimizing Warfarin Dosing using Deep Reinforcement Learning","created":"2022-02-07","cited_by_count":4,"area":null},{"id":"2202.13221","title":"RL-PGO: Reinforcement Learning-based Planar Pose-Graph Optimization","created":"2022-02-26","cited_by_count":4,"area":null},{"id":"2204.07124","title":"Learning Optimal Dynamic Treatment Regimes Using Causal Tree Methods in Medicine","created":"2022-04-14","cited_by_count":4,"area":null},{"id":"2302.04374","title":"Near-Optimal Adversarial Reinforcement Learning with Switching Costs","created":"2023-02-08","cited_by_count":4,"area":null},{"id":"2306.02910","title":"Action-Evolution Petri Nets: a Framework for Modeling and Solving Dynamic Task Assignment Problems","created":"2023-06-05","cited_by_count":4,"area":null},{"id":"2101.09571","title":"BF++: a language for general-purpose program synthesis","created":"2021-01-23","cited_by_count":3,"area":null},{"id":"2108.04087","title":"Reinforcement Learning for Intelligent Healthcare Systems: A Comprehensive Survey","created":"2021-08-05","cited_by_count":3,"area":null},{"id":"2112.09315","title":"Optimal discharge of patients from intensive care via a data-driven policy learning framework","created":"2021-12-17","cited_by_count":3,"area":null},{"id":"2112.13141","title":"On the Unreasonable Efficiency of State Space Clustering in Personalization Tasks","created":"2021-12-24","cited_by_count":3,"area":null},{"id":"2205.12418","title":"Tiered Reinforcement Learning: Pessimism in the Face of Uncertainty and Constant Regret","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2206.14198","title":"Predicting the Need for Blood Transfusion in Intensive Care Units with Reinforcement Learning","created":"2022-06-26","cited_by_count":3,"area":null},{"id":"2301.08828","title":"AI enabled RPM for Mental Health Facility","created":"2023-01-20","cited_by_count":3,"area":null},{"id":"2304.03291","title":"Comparing NARS and Reinforcement Learning: An Analysis of ONA and $Q$-Learning Algorithms","created":"2023-03-17","cited_by_count":3,"area":null},{"id":"2309.10980","title":"Adaptive Multi-Agent Deep Reinforcement Learning for Timely Healthcare Interventions","created":"2023-09-20","cited_by_count":3,"area":null},{"id":"2402.17501","title":"Intensive Care as One Big Sequence Modeling Problem","created":"2024-02-27","cited_by_count":3,"area":null},{"id":"2406.02165","title":"SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2412.04426","title":"Towards Fast Safe Online Reinforcement Learning via Policy Finetuning","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2602.08878","title":"Learning Potentials for Dynamic Matching and Application to Heart Transplantation","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2603.14003","title":"The Taxonomies, Training, and Applications of Event Stream Modelling for Electronic Health Records","created":"2026-03-14","cited_by_count":3,"area":null},{"id":"2202.04943","title":"Interpretable pipelines with evolutionarily optimized modules for RL tasks with visual inputs","created":"2022-02-10","cited_by_count":2,"area":null},{"id":"2209.09882","title":"Soft Action Priors: Towards Robust Policy Transfer","created":"2022-09-20","cited_by_count":2,"area":null},{"id":"2302.06916","title":"Effective Dimension in Bandit Problems under Censorship","created":"2023-02-14","cited_by_count":2,"area":null},{"id":"2306.12314","title":"Introspective Action Advising for Interpretable Transfer Learning","created":"2023-06-21","cited_by_count":2,"area":null},{"id":"2306.12383","title":"Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms","created":"2023-06-21","cited_by_count":2,"area":null},{"id":"2310.06835","title":"Scalable Semantic Non-Markovian Simulation Proxy for Reinforcement Learning","created":"2023-10-10","cited_by_count":2,"area":null},{"id":"2402.06388","title":"Convergence of a L2 regularized Policy Gradient Algorithm for the Multi Armed Bandit","created":"2024-02-09","cited_by_count":2,"area":null},{"id":"2404.00045","title":"Policy Optimization finds Nash Equilibrium in Regularized General-Sum LQ Games","created":"2024-03-25","cited_by_count":2,"area":null},{"id":"2407.19380","title":"Empowering Clinicians with Medical Decision Transformers: A Framework for Sepsis Treatment","created":"2024-07-28","cited_by_count":2,"area":null},{"id":"2410.03892","title":"Towards Cost Sensitive Decision Making","created":"2024-10-04","cited_by_count":2,"area":null},{"id":"2510.01620","title":"Learning to Decide with Just Enough: Information-Theoretic Context Summarization for CMDPs","created":"2025-10-02","cited_by_count":2,"area":null}],"next_cursor":"100"}