{"total":103,"rows":[{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"1811.06521","title":"Reward learning from human preferences and demonstrations in Atari","created":"2018-11-15","cited_by_count":316,"area":"alignment"},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"1810.02890","title":"HG-DAgger: Interactive Imitation Learning with Human Experts","created":"2018-10-05","cited_by_count":266,"area":"offlinerl"},{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166,"area":null},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2201.11927","title":"Constrained Variational Policy Optimization for Safe Reinforcement Learning","created":"2022-01-28","cited_by_count":71,"area":null},{"id":"2105.01984","title":"Software Engineering for AI-Based Systems: A Survey","created":"2021-05-05","cited_by_count":69,"area":null},{"id":"2302.07351","title":"Constrained Decision Transformer for Offline Safe Reinforcement Learning","created":"2023-02-14","cited_by_count":69,"area":"offlinerl"},{"id":"2405.10315","title":"TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction","created":"2024-05-16","cited_by_count":59,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2202.10341","title":"Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization","created":"2022-02-17","cited_by_count":49,"area":"driving"},{"id":"2205.14691","title":"On the Robustness of Safe Reinforcement Learning under Observational Perturbations","created":"2022-05-29","cited_by_count":38,"area":null},{"id":"2110.06831","title":"Safe Driving via Expert Guided Policy Optimization","created":"2021-10-13","cited_by_count":31,"area":"driving"},{"id":"2112.12228","title":"Direct Behavior Specification via Constrained Reinforcement Learning","created":"2021-12-22","cited_by_count":31,"area":null},{"id":"2210.10691","title":"Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes","created":"2022-10-19","cited_by_count":26,"area":null},{"id":"2201.00012","title":"MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active Learning","created":"2021-12-30","cited_by_count":25,"area":"alignment"},{"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":"2406.01309","title":"REvolve: Reward Evolution with Large Language Models using Human Feedback","created":"2024-06-03","cited_by_count":23,"area":"alignment"},{"id":"2109.12516","title":"Prioritized Experience-based Reinforcement Learning with Human Guidance for Autonomous Driving","created":"2021-09-26","cited_by_count":22,"area":"driving"},{"id":"2502.03369","title":"Learning from Active Human Involvement through Proxy Value Propagation","created":"2025-02-05","cited_by_count":19,"area":null},{"id":"2310.03718","title":"Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning","created":"2023-10-05","cited_by_count":18,"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":"2107.04200","title":"Safe Exploration by Solving Early Terminated MDP","created":"2021-07-09","cited_by_count":15,"area":null},{"id":"2302.13137","title":"A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviors","created":"2023-02-25","cited_by_count":15,"area":null},{"id":"2101.08153","title":"Shielding Atari Games with Bounded Prescience","created":"2021-01-20","cited_by_count":14,"area":null},{"id":"2107.05825","title":"Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks","created":"2021-07-13","cited_by_count":13,"area":null},{"id":"2505.17342","title":"A Survey of Safe Reinforcement Learning and Constrained MDPs: A Technical Survey on Single-Agent and Multi-Agent Safety","created":"2025-05-22","cited_by_count":13,"area":null},{"id":"2102.07716","title":"How RL Agents Behave When Their Actions Are Modified","created":"2021-02-15","cited_by_count":10,"area":null},{"id":"2502.13519","title":"MILE: Model-based Intervention Learning","created":"2025-02-19","cited_by_count":10,"area":"offlinerl"},{"id":"2102.09677","title":"Training a Resilient Q-Network against Observational Interference","created":"2021-02-18","cited_by_count":9,"area":null},{"id":"2105.01850","title":"Preference learning along multiple criteria: A game-theoretic perspective","created":"2021-05-05","cited_by_count":9,"area":null},{"id":"2412.18511","title":"Large Language Model guided Deep Reinforcement Learning for Decision Making in Autonomous Driving","created":"2024-12-24","cited_by_count":8,"area":"driving"},{"id":"2111.01616","title":"OnSlicing: Online End-to-End Network Slicing with Reinforcement Learning","created":"2021-11-02","cited_by_count":7,"area":null},{"id":"2210.14492","title":"Provable Safe Reinforcement Learning with Binary Feedback","created":"2022-10-26","cited_by_count":7,"area":null},{"id":"2011.09586","title":"SAFARI: Safe and Active Robot Imitation Learning with Imagination","created":"2020-11-18","cited_by_count":5,"area":"offlinerl"},{"id":"2102.10806","title":"Provably Correct Training of Neural Network Controllers Using Reachability Analysis","created":"2021-02-22","cited_by_count":5,"area":null},{"id":"2111.05819","title":"Look Before You Leap: Safe Model-Based Reinforcement Learning with Human Intervention","created":"2021-11-10","cited_by_count":5,"area":null},{"id":"2201.08102","title":"Safe Deep RL in 3D Environments using Human Feedback","created":"2022-01-20","cited_by_count":5,"area":"alignment"},{"id":"2406.19626","title":"Safety through feedback in Constrained RL","created":"2024-06-28","cited_by_count":5,"area":null},{"id":"2602.17588","title":"Modeling Distinct Human Interaction in Web Agents","created":"2026-02-19","cited_by_count":5,"area":"agents"},{"id":"2112.07569","title":"Cooperation for Scalable Supervision of Autonomy in Mixed Traffic","created":"2021-12-14","cited_by_count":4,"area":null},{"id":"2112.11217","title":"Model-Based Safe Reinforcement Learning with Time-Varying State and Control Constraints: An Application to Intelligent Vehicles","created":"2021-12-18","cited_by_count":4,"area":null},{"id":"2206.00152","title":"Human-AI Shared Control via Policy Dissection","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2303.14265","title":"Safe and Sample-efficient Reinforcement Learning for Clustered Dynamic Environments","created":"2023-03-24","cited_by_count":4,"area":null},{"id":"2401.12459","title":"Towards Socially and Morally Aware RL agent: Reward Design With LLM","created":"2024-01-23","cited_by_count":4,"area":"agents"},{"id":"2403.18539","title":"Safe and Robust Reinforcement Learning: Principles and Practice","created":"2024-03-27","cited_by_count":4,"area":"deeprl"},{"id":"2409.09869","title":"Critic as Lyapunov function (CALF): a model-free, stability-ensuring agent","created":"2024-09-15","cited_by_count":4,"area":"deeprl"},{"id":"2503.04969","title":"Data-Efficient Learning from Human Interventions for Mobile Robots","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2110.14615","title":"Play to Grade: Testing Coding Games as Classifying Markov Decision Process","created":"2021-10-27","cited_by_count":3,"area":null},{"id":"2111.04972","title":"Risk Sensitive Model-Based Reinforcement Learning using Uncertainty Guided Planning","created":"2021-11-09","cited_by_count":3,"area":null},{"id":"2112.03482","title":"Combining Learning from Human Feedback and Knowledge Engineering to Solve Hierarchical Tasks in Minecraft","created":"2021-12-07","cited_by_count":3,"area":"alignment"},{"id":"2209.09446","title":"A Joint Imitation-Reinforcement Learning Framework for Reduced Baseline Regret","created":"2022-09-20","cited_by_count":3,"area":null},{"id":"2209.15448","title":"Blessing from Human-AI Interaction: Super Reinforcement Learning in Confounded Environments","created":"2022-09-29","cited_by_count":3,"area":null},{"id":"2406.11039","title":"Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignment","created":"2024-06-16","cited_by_count":3,"area":"alignment"},{"id":"2407.00681","title":"Safe Reinforcement Learning for Power System Control: A Review","created":"2024-06-30","cited_by_count":3,"area":"deeprl"},{"id":"2410.05782","title":"Reinforcement Learning From Imperfect Corrective Actions And Proxy Rewards","created":"2024-10-08","cited_by_count":3,"area":"alignment"},{"id":"2501.17431","title":"Human-Aligned Skill Discovery: Balancing Behaviour Exploration and Alignment","created":"2025-01-29","cited_by_count":3,"area":"alignment"},{"id":"2503.22723","title":"Zero-Shot LLMs in Human-in-the-Loop RL: Replacing Human Feedback for Reward Shaping","created":"2025-03-26","cited_by_count":3,"area":"alignment"},{"id":"2507.00358","title":"Data-Driven Exploration for a Class of Continuous-Time Indefinite Linear--Quadratic Reinforcement Learning Problems","created":"2025-07-01","cited_by_count":3,"area":"deeprl"},{"id":"2510.01545","title":"Predictive Preference Learning from Human Interventions","created":"2025-10-02","cited_by_count":3,"area":null},{"id":"2510.26752","title":"The Oversight Game: Learning to Cooperatively Balance an AI Agent's Safety and Autonomy","created":"2025-10-30","cited_by_count":3,"area":"agents"},{"id":"2606.19998","title":"Tri-Info: Generalizable, Interpretable Failure Prediction for VLA Models via Information Theory","created":"2026-06-18","cited_by_count":3,"area":"vla"},{"id":"2111.12316","title":"A note on stabilizing reinforcement learning","created":"2021-11-24","cited_by_count":2,"area":null},{"id":"2207.08651","title":"Boolean Decision Rules for Reinforcement Learning Policy Summarisation","created":"2022-07-18","cited_by_count":2,"area":null},{"id":"2409.08382","title":"Stochastic Reinforcement Learning with Stability Guarantees for Control of Unknown Nonlinear Systems","created":"2024-09-12","cited_by_count":2,"area":"deeprl"},{"id":"2510.03485","title":"Learning Efficient Guardrails for Compliance","created":"2025-10-03","cited_by_count":2,"area":"agents"},{"id":"2602.05863","title":"Constrained Group Relative Policy Optimization","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2608.21027","title":"Don't Solve, Just Compare: Tiny Advisors for Runtime Intervention in LLM Agents","created":"2026-08-21","cited_by_count":2,"area":"agents"},{"id":"2102.13307","title":"Potential Impacts of Smart Homes on Human Behavior: A Reinforcement Learning Approach","created":"2021-02-26","cited_by_count":1,"area":null},{"id":"2307.00828","title":"Model-Assisted Probabilistic Safe Adaptive Control With Meta-Bayesian Learning","created":"2023-07-03","cited_by_count":1,"area":null},{"id":"2309.11907","title":"Learning to Recover for Safe Reinforcement Learning","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2310.11334","title":"Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2311.14270","title":"Efficient Open-world Reinforcement Learning via Knowledge Distillation and Autonomous Rule Discovery","created":"2023-11-24","cited_by_count":1,"area":"distill"},{"id":"2312.05231","title":"Modeling Risk in Reinforcement Learning: A Literature Mapping","created":"2023-12-08","cited_by_count":1,"area":null},{"id":"2404.18821","title":"Control Policy Correction Framework for Reinforcement Learning-based Energy Arbitrage Strategies","created":"2024-04-29","cited_by_count":1,"area":"deeprl"},{"id":"2406.16258","title":"MEReQ: Max-Ent Residual-Q Inverse RL for Sample-Efficient Alignment from Intervention","created":"2024-06-24","cited_by_count":1,"area":"alignment"},{"id":"2409.15688","title":"Safe Navigation for Robotic Digestive Endoscopy via Human Intervention-based Reinforcement Learning","created":"2024-09-24","cited_by_count":1,"area":"deeprl"},{"id":"2602.18603","title":"Enhancing Goal Inference via Correction Timing","created":"2026-02-20","cited_by_count":1,"area":null},{"id":"2604.13609","title":"Golden Handcuffs make safer AI agents","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2101.12509","title":"Challenges for Using Impact Regularizers to Avoid Negative Side Effects","created":"2021-01-29","cited_by_count":0,"area":null},{"id":"2207.08730","title":"A framework for online, stabilizing reinforcement learning","created":"2022-07-18","cited_by_count":0,"area":null},{"id":"2210.11259","title":"Safe Policy Improvement in Constrained Markov Decision Processes","created":"2022-10-20","cited_by_count":0,"area":null},{"id":"2211.04001","title":"Progress and summary of reinforcement learning on energy management of MPS-EV","created":"2022-11-08","cited_by_count":0,"area":null},{"id":"2212.13819","title":"Don't do it: Safer Reinforcement Learning With Rule-based Guidance","created":"2022-12-28","cited_by_count":0,"area":null},{"id":"2302.01193","title":"Imitating careful experts to avoid catastrophic events","created":"2023-02-02","cited_by_count":0,"area":null},{"id":"2305.18165","title":"An Emergency Disposal Decision-making Method with Human--Machine Collaboration","created":"2023-05-29","cited_by_count":0,"area":null},{"id":"2312.14458","title":"Multiagent Copilot Approach for Shared Autonomy between Human EEG and TD3 Deep Reinforcement Learning","created":"2023-12-22","cited_by_count":0,"area":null},{"id":"2412.07177","title":"Effective Reward Specification in Deep Reinforcement Learning","created":"2024-12-10","cited_by_count":0,"area":"deeprl"},{"id":"2506.03568","title":"Confidence-Guided Human-AI Collaboration: Reinforcement Learning with Distributional Proxy Value Propagation for Autonomous Driving","created":"2025-06-04","cited_by_count":0,"area":"driving"},{"id":"2509.03206","title":"Autonomous Learning From Success and Failure: Goal-Conditioned Supervised Learning with Negative Feedback","created":"2025-09-03","cited_by_count":0,"area":"offlinerl"},{"id":"2510.14884","title":"Learning When Not to Learn: Risk-Sensitive Abstention in Bandits with Unbounded Rewards","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2510.18478","title":"Safe But Not Sorry: Reducing Over-Conservatism in Safety Critics via Uncertainty-Aware Modulation","created":"2025-10-21","cited_by_count":0,"area":"deeprl"},{"id":"2512.09903","title":"YOPO-Nav: Visual Navigation using 3DGS Graphs from One-Pass Videos","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2601.11781","title":"Risk-Aware Human-in-the-Loop Framework with Adaptive Intrusion Response for Autonomous Vehicles","created":"2026-01-16","cited_by_count":0,"area":"driving"},{"id":"2602.03825","title":"The Geometry of Learning to Avoid Interventions","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2604.26833","title":"Rule-based High-Level Coaching for Goal-Conditioned Reinforcement Learning in Search-and-Rescue UAV Missions Under Limited-Simulation Training","created":"2026-04-29","cited_by_count":0,"area":"deeprl"},{"id":"2605.09818","title":"Learning to Compress Time-to-Control: A Reinforcement Learning Framework for Chronic Disease Management","created":"2026-05-10","cited_by_count":0,"area":"offlinerl"},{"id":"2607.01251","title":"Collaborative Disagreement Resolution for Scalable Oversight","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2607.08925","title":"SafeExplorer: An Unbiased Policy Gradient for Reinforcement Learning with Recovery Interventions","created":"2026-07-09","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}