{"total":214,"rows":[{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"area":"alignment"},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2110.15191","title":"URLB: Unsupervised Reinforcement Learning Benchmark","created":"2021-10-28","cited_by_count":139,"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":"2108.00401","title":"Advances in adversarial attacks and defenses in computer vision: A survey","created":"2021-08-01","cited_by_count":127,"area":null},{"id":"2110.05038","title":"Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs","created":"2021-10-11","cited_by_count":122,"area":null},{"id":"2206.02829","title":"RORL: Robust Offline Reinforcement Learning via Conservative Smoothing","created":"2022-06-06","cited_by_count":84,"area":"offlinerl"},{"id":"2308.12833","title":"Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities","created":"2023-08-24","cited_by_count":82,"area":null},{"id":"2505.02077","title":"Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents","created":"2025-05-04","cited_by_count":71,"area":"safety"},{"id":"2105.00579","title":"BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning","created":"2021-05-02","cited_by_count":68,"area":null},{"id":"2206.05862","title":"X-Risk Analysis for AI Research","created":"2022-06-13","cited_by_count":60,"area":null},{"id":"2106.05087","title":"Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL","created":"2021-06-09","cited_by_count":55,"area":null},{"id":"2202.10910","title":"Sound Adversarial Audio-Visual Navigation","created":"2022-02-22","cited_by_count":48,"area":null},{"id":"2401.04536","title":"Evaluating Language Model Agency through Negotiations","created":"2024-01-09","cited_by_count":48,"area":null},{"id":"2210.05927","title":"Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning","created":"2022-10-12","cited_by_count":43,"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":"2106.11420","title":"Policy Smoothing for Provably Robust Reinforcement Learning","created":"2021-06-21","cited_by_count":40,"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":"2409.15360","title":"Reward-Robust RLHF in LLMs","created":"2024-09-18","cited_by_count":32,"area":"alignment"},{"id":"2312.12585","title":"BadRL: Sparse Targeted Backdoor Attack Against Reinforcement Learning","created":"2023-12-19","cited_by_count":30,"area":null},{"id":"2211.00241","title":"Adversarial Policies Beat Superhuman Go AIs","created":"2022-11-01","cited_by_count":29,"area":null},{"id":"2101.05507","title":"Evaluating the Robustness of Collaborative Agents","created":"2021-01-14","cited_by_count":25,"area":null},{"id":"2506.14261","title":"RL-Obfuscation: Can Language Models Learn to Evade Latent-Space Monitors?","created":"2025-06-17","cited_by_count":24,"area":null},{"id":"2209.13020","title":"Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humans","created":"2022-09-14","cited_by_count":23,"area":null},{"id":"2509.22047","title":"MO-GRPO: Mitigating Reward Hacking of Group Relative Policy Optimization on Multi-Objective Problems","created":"2025-09-26","cited_by_count":23,"area":"lr"},{"id":"2109.03540","title":"A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions","created":"2021-09-08","cited_by_count":21,"area":null},{"id":"2204.07932","title":"Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learning","created":"2022-04-17","cited_by_count":21,"area":null},{"id":"2206.01888","title":"Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learning","created":"2022-06-04","cited_by_count":20,"area":"offlinerl"},{"id":"2202.03609","title":"PolicyCleanse: Backdoor Detection and Mitigation in Reinforcement Learning","created":"2022-02-08","cited_by_count":19,"area":null},{"id":"2301.07487","title":"Adversarial Robust Deep Reinforcement Learning Requires Redefining Robustness","created":"2023-01-17","cited_by_count":19,"area":null},{"id":"2405.20539","title":"SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents","created":"2024-05-30","cited_by_count":19,"area":"safety"},{"id":"2102.09701","title":"Center Smoothing: Certified Robustness for Networks with Structured Outputs","created":"2021-02-19","cited_by_count":18,"area":null},{"id":"2108.03803","title":"Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learning","created":"2021-08-09","cited_by_count":18,"area":null},{"id":"2405.19424","title":"Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policies","created":"2024-05-29","cited_by_count":18,"area":"diffusion"},{"id":"2109.06795","title":"ROMAX: Certifiably Robust Deep Multiagent Reinforcement Learning via Convex Relaxation","created":"2021-09-14","cited_by_count":17,"area":null},{"id":"2302.03322","title":"Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence","created":"2023-02-07","cited_by_count":17,"area":null},{"id":"2308.10797","title":"Stabilizing Unsupervised Environment Design with a Learned Adversary","created":"2023-08-21","cited_by_count":17,"area":null},{"id":"2211.11030","title":"Adversarial Cheap Talk","created":"2022-11-20","cited_by_count":16,"area":null},{"id":"2412.10713","title":"RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors","created":"2024-12-14","cited_by_count":16,"area":"deeprl"},{"id":"2106.15587","title":"Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentation","created":"2021-06-29","cited_by_count":15,"area":null},{"id":"2108.13093","title":"Investigating Vulnerabilities of Deep Neural Policies","created":"2021-08-30","cited_by_count":15,"area":null},{"id":"2104.03356","title":"Universal Spectral Adversarial Attacks for Deformable Shapes","created":"2021-04-07","cited_by_count":14,"area":null},{"id":"2110.01388","title":"Neural Network Verification in Control","created":"2021-09-30","cited_by_count":14,"area":null},{"id":"2211.03769","title":"Are AlphaZero-like Agents Robust to Adversarial Perturbations?","created":"2022-11-07","cited_by_count":14,"area":null},{"id":"2302.13851","title":"Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attacks","created":"2023-02-27","cited_by_count":14,"area":null},{"id":"2405.12424","title":"Rethinking Robustness Assessment: Adversarial Attacks on Learning-based Quadrupedal Locomotion Controllers","created":"2024-05-21","cited_by_count":14,"area":"deeprl"},{"id":"2103.06473","title":"Multi-Task Federated Reinforcement Learning with Adversaries","created":"2021-03-11","cited_by_count":13,"area":null},{"id":"2109.07723","title":"Targeted Attack on Deep RL-based Autonomous Driving with Learned Visual Patterns","created":"2021-09-16","cited_by_count":13,"area":"driving"},{"id":"2304.05370","title":"Overload: Latency Attacks on Object Detection for Edge Devices","created":"2023-04-11","cited_by_count":13,"area":null},{"id":"2112.02807","title":"MDPFuzz: Testing Models Solving Markov Decision Processes","created":"2021-12-06","cited_by_count":12,"area":null},{"id":"2112.09025","title":"Deep Reinforcement Learning Policies Learn Shared Adversarial Features Across MDPs","created":"2021-12-16","cited_by_count":12,"area":null},{"id":"2505.18126","title":"Reward Model Overoptimisation in Iterated RLHF","created":"2025-05-23","cited_by_count":12,"area":"alignment"},{"id":"2505.23847","title":"Seven Security Challenges in Cross-domain Multi-agent LLM Systems","created":"2025-05-28","cited_by_count":12,"area":"agents"},{"id":"2102.07244","title":"Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPS","created":"2021-02-14","cited_by_count":10,"area":null},{"id":"2112.11937","title":"Adversarial Deep Reinforcement Learning for Improving the Robustness of Multi-agent Autonomous Driving Policies","created":"2021-12-22","cited_by_count":10,"area":"driving"},{"id":"2307.07670","title":"Efficient Adversarial Attacks on Online Multi-agent Reinforcement Learning","created":"2023-07-15","cited_by_count":10,"area":null},{"id":"2311.01642","title":"Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula","created":"2023-11-03","cited_by_count":10,"area":null},{"id":"2106.08746","title":"Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defenses","created":"2021-06-16","cited_by_count":9,"area":null},{"id":"2105.12189","title":"Robust Value Iteration for Continuous Control Tasks","created":"2021-05-25","cited_by_count":8,"area":null},{"id":"2110.08956","title":"Improving Robustness of Reinforcement Learning for Power System Control with Adversarial Training","created":"2021-10-18","cited_by_count":8,"area":null},{"id":"2206.07188","title":"Defending Observation Attacks in Deep Reinforcement Learning via Detection and Denoising","created":"2022-06-14","cited_by_count":8,"area":null},{"id":"2401.02349","title":"A Survey Analyzing Generalization in Deep Reinforcement Learning","created":"2024-01-04","cited_by_count":8,"area":"deeprl"},{"id":"2402.12673","title":"Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies","created":"2024-02-20","cited_by_count":8,"area":"deeprl"},{"id":"2410.13995","title":"Adversarial Inception Backdoor Attacks against Reinforcement Learning","created":"2024-10-17","cited_by_count":8,"area":"deeprl"},{"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":"2207.00694","title":"Efficient Adversarial Training With Data Pruning","created":"2022-07-01","cited_by_count":7,"area":null},{"id":"2212.11746","title":"Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning","created":"2022-12-22","cited_by_count":7,"area":null},{"id":"2305.17342","title":"Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL","created":"2023-05-27","cited_by_count":7,"area":null},{"id":"2306.05873","title":"Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisions","created":"2023-06-09","cited_by_count":7,"area":null},{"id":"2402.03590","title":"Assessing the Impact of Distribution Shift on Reinforcement Learning Performance","created":"2024-02-05","cited_by_count":7,"area":"deeprl"},{"id":"2402.03741","title":"SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems","created":"2024-02-06","cited_by_count":7,"area":null},{"id":"2605.23220","title":"WMAttack: Automated Attack Search for Adversarial Evaluation of World-Model Agents","created":"2026-05-22","cited_by_count":7,"area":"wm"},{"id":"2104.10262","title":"Network Defense is Not a Game","created":"2021-04-20","cited_by_count":6,"area":null},{"id":"2110.01954","title":"Continuous-Time Fitted Value Iteration for Robust Policies","created":"2021-10-05","cited_by_count":6,"area":null},{"id":"2207.05729","title":"Physical Passive Patch Adversarial Attacks on Visual Odometry Systems","created":"2022-07-11","cited_by_count":6,"area":null},{"id":"2301.12595","title":"Adversarial Attacks on Adversarial Bandits","created":"2023-01-30","cited_by_count":6,"area":null},{"id":"2310.09833","title":"Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization","created":"2023-10-15","cited_by_count":6,"area":null},{"id":"2312.07392","title":"ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learning","created":"2023-12-12","cited_by_count":6,"area":null},{"id":"2112.05495","title":"How Private Is Your RL Policy? An Inverse RL Based Analysis Framework","created":"2021-12-10","cited_by_count":5,"area":null},{"id":"2212.05337","title":"Targeted Adversarial Attacks on Deep Reinforcement Learning Policies via Model Checking","created":"2022-12-10","cited_by_count":5,"area":null},{"id":"2312.13435","title":"The Adaptive Arms Race: Redefining Robustness in AI Security","created":"2023-12-20","cited_by_count":5,"area":null},{"id":"2501.15529","title":"UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning","created":"2025-01-26","cited_by_count":5,"area":"deeprl"},{"id":"2205.10098","title":"Adversarial joint attacks on legged robots","created":"2022-05-20","cited_by_count":4,"area":null},{"id":"2207.09597","title":"Feasible Adversarial Robust Reinforcement Learning for Underspecified Environments","created":"2022-07-19","cited_by_count":4,"area":null},{"id":"2208.05083","title":"Reducing Exploitability with Population Based Training","created":"2022-08-10","cited_by_count":4,"area":null},{"id":"2402.02165","title":"Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error","created":"2024-02-03","cited_by_count":4,"area":"deeprl"},{"id":"2403.07933","title":"Corruption-Robust Offline Two-Player Zero-Sum Markov Games","created":"2024-03-04","cited_by_count":4,"area":null},{"id":"2404.04714","title":"Data Poisoning Attacks on Off-Policy Policy Evaluation Methods","created":"2024-04-06","cited_by_count":4,"area":"safety"},{"id":"2506.05070","title":"RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation","created":"2025-06-05","cited_by_count":4,"area":"alignment"},{"id":"2509.16950","title":"Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving","created":"2025-09-21","cited_by_count":4,"area":"safety"},{"id":"2602.08690","title":"SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity","created":"2026-02-09","cited_by_count":4,"area":"deeprl"},{"id":"2607.15207","title":"BadWAM: When World-Action Models Dream Right but Act Wrong","created":"2026-07-16","cited_by_count":4,"area":"wm"},{"id":"2106.06060","title":"AI-driven Prices for Externalities and Sustainability in Production Markets","created":"2021-06-10","cited_by_count":3,"area":null},{"id":"2107.04487","title":"ARC: Adversarially Robust Control Policies for Autonomous Vehicles","created":"2021-07-09","cited_by_count":3,"area":"driving"},{"id":"2109.03975","title":"Membership Inference Attacks Against Temporally Correlated Data in Deep Reinforcement Learning","created":"2021-09-08","cited_by_count":3,"area":"safety"},{"id":"2112.00940","title":"Reward-Free Attacks in Multi-Agent Reinforcement Learning","created":"2021-12-02","cited_by_count":3,"area":null},{"id":"2210.11237","title":"Emerging Threats in Deep Learning-Based Autonomous Driving: A Comprehensive Survey","created":"2022-10-19","cited_by_count":3,"area":null},{"id":"2301.04299","title":"SoK: Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning","created":"2023-01-11","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":"2302.06912","title":"Regret-Based Defense in Adversarial Reinforcement Learning","created":"2023-02-14","cited_by_count":3,"area":null}],"next_cursor":"100"}