{"total":124,"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":"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":"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":"2106.09292","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":"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":"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":"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":"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":"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":"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":"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":"2110.08984","title":"Optimistic Policy Optimization is Provably Efficient in Non-stationary MDPs","created":"2021-10-18","cited_by_count":16,"area":null},{"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":"2301.11518","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":"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":"2103.08741","title":"Deep Reinforcement Learning for Band Selection in Hyperspectral Image Classification","created":"2021-03-15","cited_by_count":12,"area":null},{"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":"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":"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":"2205.13697","title":"FedFormer: Contextual Federation with Attention in Reinforcement Learning","created":"2022-05-27","cited_by_count":8,"area":null},{"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":"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":"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":"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},{"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":"2401.15803","title":"GarchingSim: An Autonomous Driving Simulator with Photorealistic Scenes and Minimalist Workflow","created":"2024-01-28","cited_by_count":5,"area":null},{"id":"2406.07944","title":"Enhancing Differential Testing With LLMs For Testing Deep Learning Libraries","created":"2024-06-12","cited_by_count":5,"area":null},{"id":"2104.05931","title":"Two-stage training algorithm for AI robot soccer","created":"2021-04-13","cited_by_count":4,"area":null},{"id":"2208.01508","title":"COMET: Coverage-guided Model Generation For Deep Learning Library Testing","created":"2022-08-02","cited_by_count":4,"area":null},{"id":"2310.18601","title":"Online Decision Mediation","created":"2023-10-28","cited_by_count":4,"area":null},{"id":"2311.03564","title":"Low-Rank MDPs with Continuous Action Spaces","created":"2023-11-06","cited_by_count":4,"area":null},{"id":"2312.04688","title":"Federated Learning for 6G: Paradigms, Taxonomy, Recent Advances and Insights","created":"2023-12-07","cited_by_count":4,"area":null},{"id":"2103.15941","title":"Shaping Advice in Deep Multi-Agent Reinforcement Learning","created":"2021-03-29","cited_by_count":3,"area":null},{"id":"2105.07526","title":"DRAS-CQSim: A Reinforcement Learning based Framework for HPC Cluster Scheduling","created":"2021-05-16","cited_by_count":3,"area":null},{"id":"2108.13930","title":"EG-Booster: Explanation-Guided Booster of ML Evasion Attacks","created":"2021-08-31","cited_by_count":3,"area":null},{"id":"2109.06523","title":"Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems through Probabilistic Model Checking","created":"2021-09-14","cited_by_count":3,"area":null},{"id":"2201.01289","title":"Self-directed Machine Learning","created":"2022-01-04","cited_by_count":3,"area":null},{"id":"2301.11374","title":"Certifiably Robust Reinforcement Learning through Model-Based Abstract Interpretation","created":"2023-01-26","cited_by_count":3,"area":null},{"id":"2304.00420","title":"Experimentation Platforms Meet Reinforcement Learning: Bayesian Sequential Decision-Making for Continuous Monitoring","created":"2023-04-02","cited_by_count":3,"area":null},{"id":"2108.08655","title":"Global Convergence of the ODE Limit for Online Actor-Critic Algorithms in Reinforcement Learning","created":"2021-08-19","cited_by_count":2,"area":null},{"id":"2111.04865","title":"On Assessing The Safety of Reinforcement Learning algorithms Using Formal Methods","created":"2021-11-08","cited_by_count":2,"area":null},{"id":"2203.04927","title":"Investigation of Factorized Optical Flows as Mid-Level Representations","created":"2022-03-09","cited_by_count":2,"area":null},{"id":"2204.12748","title":"Self-Driving Car Steering Angle Prediction: Let Transformer Be a Car Again","created":"2022-04-27","cited_by_count":2,"area":null},{"id":"2206.07321","title":"Morphence-2.0: Evasion-Resilient Moving Target Defense Powered by Out-of-Distribution Detection","created":"2022-06-15","cited_by_count":2,"area":null},{"id":"2210.15670","title":"Knowledge-Guided Exploration in Deep Reinforcement Learning","created":"2022-10-26","cited_by_count":2,"area":null},{"id":"2310.04772","title":"Optimal Sequential Decision-Making in Geosteering: A Reinforcement Learning Approach","created":"2023-10-07","cited_by_count":2,"area":null},{"id":"2312.14941","title":"Multi-Criteria Client Selection and Scheduling with Fairness Guarantee for Federated Learning Service","created":"2023-12-05","cited_by_count":2,"area":null},{"id":"2410.09134","title":"Multi-Agent Actor-Critics in Autonomous Cyber Defense","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2101.06248","title":"Local Navigation and Docking of an Autonomous Robot Mower using Reinforcement Learning and Computer Vision","created":"2021-01-15","cited_by_count":1,"area":null},{"id":"2104.02188","title":"GPU Domain Specialization via Composable On-Package Architecture","created":"2021-04-05","cited_by_count":1,"area":null},{"id":"2105.05817","title":"Adversarial Reinforcement Learning in Dynamic Channel Access and Power Control","created":"2021-05-12","cited_by_count":1,"area":null},{"id":"2109.05710","title":"Robust Stability of Neural Network-controlled Nonlinear Systems with Parametric Variability","created":"2021-09-13","cited_by_count":1,"area":null},{"id":"2111.14204","title":"Count-Based Temperature Scheduling for Maximum Entropy Reinforcement Learning","created":"2021-11-28","cited_by_count":1,"area":null},{"id":"2202.03263","title":"Asynchronous Parallel Incremental Block-Coordinate Descent for Decentralized Machine Learning","created":"2022-02-07","cited_by_count":1,"area":null},{"id":"2202.05135","title":"Group-Agent Reinforcement Learning","created":"2022-02-10","cited_by_count":1,"area":null},{"id":"2204.10372","title":"Model-free Learning of Regions of Attraction via Recurrent Sets","created":"2022-04-21","cited_by_count":1,"area":null},{"id":"2207.03484","title":"AVDDPG: Federated reinforcement learning applied to autonomous platoon control","created":"2022-07-05","cited_by_count":1,"area":null},{"id":"2304.12151","title":"Policy Resilience to Environment Poisoning Attacks on Reinforcement Learning","created":"2023-04-24","cited_by_count":1,"area":null},{"id":"2306.04299","title":"Timing Process Interventions with Causal Inference and Reinforcement Learning","created":"2023-06-07","cited_by_count":1,"area":null},{"id":"2402.14580","title":"Savvy: Trustworthy Autonomous Vehicles Architecture","created":"2024-02-08","cited_by_count":1,"area":null},{"id":"2502.04201","title":"Safeguarding connected autonomous vehicle communication: Protocols, intra- and inter-vehicular attacks and defenses","created":"2025-02-06","cited_by_count":1,"area":null},{"id":"2604.23105","title":"Transferable Physical-World Adversarial Patches Against Object Detection in Autonomous Driving","created":"2026-04-25","cited_by_count":1,"area":null},{"id":"2607.17290","title":"Lookahead Branching for Neural Network Verification","created":"2026-07-19","cited_by_count":1,"area":null},{"id":"2101.01042","title":"Fast Ensemble Learning Using Adversarially-Generated Restricted Boltzmann Machines","created":"2021-01-04","cited_by_count":0,"area":null}],"next_cursor":"100"}