{"total":225,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920,"area":"offlinerl"},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590,"area":"offlinerl"},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"area":null},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2101.08452","title":"Robust Reinforcement Learning on State Observations with Learned Optimal Adversary","created":"2021-01-21","cited_by_count":135,"area":null},{"id":"2207.05382","title":"Frequency Domain Model Augmentation for Adversarial Attack","created":"2022-07-12","cited_by_count":130,"area":null},{"id":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95,"area":null},{"id":"2108.11887","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","created":"2021-08-26","cited_by_count":81,"area":null},{"id":"2111.10919","title":"Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation","created":"2021-11-21","cited_by_count":71,"area":"offlinerl"},{"id":"2102.13185","title":"Off-Policy Imitation Learning from Observations","created":"2021-02-25","cited_by_count":70,"area":"offlinerl"},{"id":"2206.09682","title":"SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles","created":"2022-06-20","cited_by_count":66,"area":"driving"},{"id":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60,"area":null},{"id":"2106.02748","title":"Decentralized Q-Learning in Zero-sum Markov Games","created":"2021-06-04","cited_by_count":58,"area":null},{"id":"2204.00755","title":"Safe Reinforcement Learning via Shielding under Partial Observability","created":"2022-04-02","cited_by_count":56,"area":null},{"id":"2102.07952","title":"A Survey of Machine Learning for Computer Architecture and Systems","created":"2021-02-16","cited_by_count":53,"area":null},{"id":"2102.01168","title":"Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges","created":"2021-01-27","cited_by_count":50,"area":null},{"id":"2112.06569","title":"Triangle Attack: A Query-efficient Decision-based Adversarial Attack","created":"2021-12-13","cited_by_count":48,"area":null},{"id":"2106.06431","title":"Offline Reinforcement Learning as Anti-Exploration","created":"2021-06-11","cited_by_count":44,"area":"offlinerl"},{"id":"2106.09292","title":"CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing","created":"2021-06-17","cited_by_count":42,"area":null},{"id":"2106.15691","title":"Deep Multiagent Reinforcement Learning: Challenges and Directions","created":"2021-06-29","cited_by_count":42,"area":null},{"id":"2212.06437","title":"DiffStack: A Differentiable and Modular Control Stack for Autonomous Vehicles","created":"2022-12-13","cited_by_count":37,"area":"driving"},{"id":"2105.04646","title":"Deeply-Debiased Off-Policy Interval Estimation","created":"2021-05-10","cited_by_count":36,"area":null},{"id":"2305.18901","title":"Policy Optimization for Continuous Reinforcement Learning","created":"2023-05-30","cited_by_count":31,"area":null},{"id":"2110.07067","title":"Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration Enhancement","created":"2021-10-13","cited_by_count":29,"area":"driving"},{"id":"2103.10290","title":"Integrated Decision and Control: Towards Interpretable and Computationally Efficient Driving Intelligence","created":"2021-03-18","cited_by_count":27,"area":"driving"},{"id":"2111.07695","title":"Joint Synthesis of Safety Certificate and Safe Control Policy using Constrained Reinforcement Learning","created":"2021-11-15","cited_by_count":27,"area":null},{"id":"2107.04271","title":"FedAdapt: Adaptive Offloading for IoT Devices in Federated Learning","created":"2021-07-09","cited_by_count":26,"area":null},{"id":"2108.03706","title":"Online Bootstrap Inference For Policy Evaluation in Reinforcement Learning","created":"2021-08-08","cited_by_count":26,"area":null},{"id":"2203.08398","title":"COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks","created":"2022-03-16","cited_by_count":26,"area":"offlinerl"},{"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":"2210.04688","title":"BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets","created":"2022-10-07","cited_by_count":25,"area":"offlinerl"},{"id":"2212.02705","title":"What is the Solution for State-Adversarial Multi-Agent Reinforcement Learning?","created":"2022-12-06","cited_by_count":22,"area":null},{"id":"2206.00810","title":"Offline Reinforcement Learning with Differential Privacy","created":"2022-06-02","cited_by_count":20,"area":"offlinerl"},{"id":"2310.13565","title":"Reward Shaping for Happier Autonomous Cyber Security Agents","created":"2023-10-20","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":"2101.06778","title":"A Safe Hierarchical Planning Framework for Complex Driving Scenarios based on Reinforcement Learning","created":"2021-01-17","cited_by_count":18,"area":"driving"},{"id":"2103.07932","title":"Gym-ANM: Reinforcement Learning Environments for Active Network Management Tasks in Electricity Distribution Systems","created":"2021-03-14","cited_by_count":18,"area":null},{"id":"2112.12591","title":"Black-Box Testing of Deep Neural Networks Through Test Case Diversity","created":"2021-12-20","cited_by_count":18,"area":null},{"id":"2401.10314","title":"LangProp: A code optimization framework using Large Language Models applied to driving","created":"2024-01-18","cited_by_count":18,"area":"driving"},{"id":"2101.00240","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","created":"2021-01-01","cited_by_count":17,"area":null},{"id":"2106.12729","title":"Finite-Sample Analysis of Off-Policy TD-Learning via Generalized Bellman Operators","created":"2021-06-24","cited_by_count":17,"area":null},{"id":"2306.09318","title":"Inroads into Autonomous Network Defence using Explained Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2104.07246","title":"Human-in-the-Loop Deep Reinforcement Learning with Application to Autonomous Driving","created":"2021-04-15","cited_by_count":16,"area":"driving"},{"id":"2110.08984","title":"Optimistic Policy Optimization is Provably Efficient in Non-stationary MDPs","created":"2021-10-18","cited_by_count":16,"area":null},{"id":"2201.07833","title":"Hybrid Reinforcement Learning-Based Eco-Driving Strategy for Connected and Automated Vehicles at Signalized Intersections","created":"2022-01-19","cited_by_count":16,"area":"driving"},{"id":"2202.08557","title":"CADRE: A Cascade Deep Reinforcement Learning Framework for Vision-based Autonomous Urban Driving","created":"2022-02-17","cited_by_count":16,"area":"driving"},{"id":"2206.14302","title":"Reinforcement Learning in Medical Image Analysis: Concepts, Applications, Challenges, and Future Directions","created":"2022-06-28","cited_by_count":16,"area":null},{"id":"2210.08857","title":"On the convergence of policy gradient methods to Nash equilibria in general stochastic games","created":"2022-10-17","cited_by_count":16,"area":null},{"id":"2212.04680","title":"Near-Optimal Differentially Private Reinforcement Learning","created":"2022-12-09","cited_by_count":16,"area":null},{"id":"2301.12203","title":"SaFormer: A Conditional Sequence Modeling Approach to Offline Safe Reinforcement Learning","created":"2023-01-28","cited_by_count":16,"area":"offlinerl"},{"id":"2301.11518","title":"Online Learning in Stackelberg Games with an Omniscient Follower","created":"2023-01-27","cited_by_count":15,"area":null},{"id":"2108.00358","title":"Applications of Artificial Neural Networks in Microorganism Image Analysis: A Comprehensive Review from Conventional Multilayer Perceptron to Popular Convolutional Neural Network and Potential Visual Transformer","created":"2021-08-01","cited_by_count":14,"area":null},{"id":"2211.15956","title":"Offline Reinforcement Learning with Closed-Form Policy Improvement Operators","created":"2022-11-29","cited_by_count":14,"area":"offlinerl"},{"id":"2307.02842","title":"Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback","created":"2023-07-06","cited_by_count":14,"area":"alignment"},{"id":"2104.05996","title":"Fall of Giants: How popular text-based MLaaS fall against a simple evasion attack","created":"2021-04-13","cited_by_count":13,"area":null},{"id":"2304.04660","title":"Uncertainty-driven Trajectory Truncation for Data Augmentation in Offline Reinforcement Learning","created":"2023-04-10","cited_by_count":13,"area":"offlinerl"},{"id":"2309.01448","title":"Hundreds Guide Millions: Adaptive Offline Reinforcement Learning with Expert Guidance","created":"2023-09-04","cited_by_count":13,"area":"offlinerl"},{"id":"2103.08741","title":"Deep Reinforcement Learning for Band Selection in Hyperspectral Image Classification","created":"2021-03-15","cited_by_count":12,"area":null},{"id":"2401.11555","title":"VQC-Based Reinforcement Learning with Data Re-uploading: Performance and Trainability","created":"2024-01-21","cited_by_count":12,"area":"deeprl"},{"id":"1803.01129","title":"OIL: Observational Imitation Learning","created":"2018-03-03","cited_by_count":11,"area":"offlinerl"},{"id":"2105.01006","title":"Robotic Surgery With Lean Reinforcement Learning","created":"2021-05-03","cited_by_count":11,"area":null},{"id":"2206.09603","title":"Constrained Reinforcement Learning for Robotics via Scenario-Based Programming","created":"2022-06-20","cited_by_count":11,"area":null},{"id":"2207.01898","title":"\"Even if ...\" -- Diverse Semifactual Explanations of Reject","created":"2022-07-05","cited_by_count":11,"area":null},{"id":"2403.02290","title":"Koopman-Assisted Reinforcement Learning","created":"2024-03-04","cited_by_count":11,"area":"deeprl"},{"id":"2501.16733","title":"Dream to Drive with Predictive Individual World Model","created":"2025-01-28","cited_by_count":11,"area":"wm"},{"id":"2505.19281","title":"A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning","created":"2025-05-25","cited_by_count":11,"area":"deeprl"},{"id":"2102.06243","title":"Deep Reinforcement Agent for Scheduling in HPC","created":"2021-02-11","cited_by_count":10,"area":null},{"id":"2201.11965","title":"Provably Efficient Primal-Dual Reinforcement Learning for CMDPs with Non-stationary Objectives and Constraints","created":"2022-01-28","cited_by_count":10,"area":null},{"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":"2412.19436","title":"Low-Rank Contextual Reinforcement Learning from Heterogeneous Human Feedback","created":"2024-12-27","cited_by_count":10,"area":"alignment"},{"id":"2102.09751","title":"PRICURE: Privacy-Preserving Collaborative Inference in a Multi-Party Setting","created":"2021-02-19","cited_by_count":9,"area":"safety"},{"id":"2103.13861","title":"Hierarchical Program-Triggered Reinforcement Learning Agents For Automated Driving","created":"2021-03-25","cited_by_count":9,"area":"driving"},{"id":"2108.13952","title":"Morphence: Moving Target Defense Against Adversarial Examples","created":"2021-08-31","cited_by_count":9,"area":null},{"id":"2109.05507","title":"Check Your Other Door! Creating Backdoor Attacks in the Frequency Domain","created":"2021-09-12","cited_by_count":9,"area":null},{"id":"2201.04612","title":"Agent-Temporal Attention for Reward Redistribution in Episodic Multi-Agent Reinforcement Learning","created":"2022-01-12","cited_by_count":9,"area":null},{"id":"2405.11982","title":"Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space","created":"2024-05-20","cited_by_count":9,"area":"deeprl"},{"id":"2205.13697","title":"FedFormer: Contextual Federation with Attention in Reinforcement Learning","created":"2022-05-27","cited_by_count":8,"area":null},{"id":"2406.10540","title":"Generating and Evolving Reward Functions for Highway Driving with Large Language Models","created":"2024-06-15","cited_by_count":8,"area":"driving"},{"id":"2109.04298","title":"Quantum Machine Learning for Finance","created":"2021-09-09","cited_by_count":7,"area":null},{"id":"2202.07244","title":"Explaining Reject Options of Learning Vector Quantization Classifiers","created":"2022-02-15","cited_by_count":7,"area":null},{"id":"2205.07623","title":"Model Agnostic Local Explanations of Reject","created":"2022-05-16","cited_by_count":7,"area":null},{"id":"2206.10158","title":"Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems","created":"2022-06-21","cited_by_count":7,"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":"2302.11510","title":"Selective experience replay compression using coresets for lifelong deep reinforcement learning in medical imaging","created":"2023-02-22","cited_by_count":7,"area":null},{"id":"2303.14281","title":"Sequential Knockoffs for Variable Selection in Reinforcement Learning","created":"2023-03-24","cited_by_count":7,"area":null},{"id":"2312.06436","title":"Reward Certification for Policy Smoothed Reinforcement Learning","created":"2023-12-11","cited_by_count":7,"area":null},{"id":"2401.13205","title":"Boosting the Transferability of Adversarial Examples via Local Mixup and Adaptive Step Size","created":"2024-01-24","cited_by_count":7,"area":null},{"id":"2509.08221","title":"A Comprehensive Review of Reinforcement Learning for Autonomous Driving in the CARLA Simulator","created":"2025-09-10","cited_by_count":7,"area":"driving"},{"id":"2105.08846","title":"Gym-ANM: Open-source software to leverage reinforcement learning for power system management in research and education","created":"2021-05-18","cited_by_count":6,"area":null},{"id":"2106.15820","title":"Explanation-Guided Diagnosis of Machine Learning Evasion Attacks","created":"2021-06-30","cited_by_count":6,"area":null},{"id":"2109.07752","title":"Deep Visual Navigation under Partial Observability","created":"2021-09-16","cited_by_count":6,"area":null},{"id":"2308.01649","title":"MARLIM: Multi-Agent Reinforcement Learning for Inventory Management","created":"2023-08-03","cited_by_count":6,"area":null},{"id":"2403.18965","title":"LORD: Large Models based Opposite Reward Design for Autonomous Driving","created":"2024-03-27","cited_by_count":6,"area":"driving"},{"id":"2410.14468","title":"Knowledge Transfer from Simple to Complex: A Safe and Efficient Reinforcement Learning Framework for Autonomous Driving Decision-Making","created":"2024-10-18","cited_by_count":6,"area":"driving"},{"id":"2505.24161","title":"Proxy Target: Bridging the Gap Between Discrete Spiking Neural Networks and Continuous Control","created":"2025-05-30","cited_by_count":6,"area":"deeprl"},{"id":"2512.01993","title":"RoaD: Rollouts as Demonstrations for Closed-Loop Supervised Fine-Tuning of Autonomous Driving Policies","created":"2025-12-01","cited_by_count":6,"area":"driving"},{"id":"2105.06517","title":"Reinforcement Learning Based Safe Decision Making for Highway Autonomous Driving","created":"2021-05-13","cited_by_count":5,"area":"driving"},{"id":"2108.03952","title":"Safe Deep Reinforcement Learning for Multi-Agent Systems with Continuous Action Spaces","created":"2021-08-09","cited_by_count":5,"area":null},{"id":"2207.02162","title":"Tackling Real-World Autonomous Driving using Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":5,"area":"driving"},{"id":"2309.01194","title":"A Survey on Service Route and Time Prediction in Instant Delivery: Taxonomy, Progress, and Prospects","created":"2023-09-03","cited_by_count":5,"area":null}],"next_cursor":"100"}