{"total":93,"rows":[{"id":"2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","created":"2023-04-12","cited_by_count":1045,"area":null},{"id":"2109.10862","title":"Recursively Summarizing Books with Human Feedback","created":"2021-09-22","cited_by_count":290,"area":null},{"id":"2303.00001","title":"Reward Design with Language Models","created":"2023-02-27","cited_by_count":261,"area":null},{"id":"2212.09611","title":"Optimizing Prompts for Text-to-Image Generation","created":"2022-12-19","cited_by_count":207,"area":null},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168,"area":null},{"id":"2105.14111","title":"Goal Misgeneralization in Deep Reinforcement Learning","created":"2021-05-28","cited_by_count":123,"area":null},{"id":"2111.03026","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","created":"2021-11-04","cited_by_count":106,"area":null},{"id":"2111.04850","title":"Dueling RL: Reinforcement Learning with Trajectory Preferences","created":"2021-11-08","cited_by_count":106,"area":null},{"id":"2203.15103","title":"Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions","created":"2022-03-28","cited_by_count":89,"area":null},{"id":"2202.08137","title":"A data-driven approach for learning to control computers","created":"2022-02-16","cited_by_count":88,"area":null},{"id":"2303.00957","title":"Preference Transformer: Modeling Human Preferences using Transformers for RL","created":"2023-03-02","cited_by_count":79,"area":null},{"id":"2311.17391","title":"Unveiling the Implicit Toxicity in Large Language Models","created":"2023-11-29","cited_by_count":51,"area":null},{"id":"2203.07475","title":"Invariance in Policy Optimisation and Partial Identifiability in Reward Learning","created":"2022-03-14","cited_by_count":46,"area":null},{"id":"2310.09144","title":"Goodhart's Law in Reinforcement Learning","created":"2023-10-13","cited_by_count":41,"area":null},{"id":"2103.04529","title":"Self-Supervised Online Reward Shaping in Sparse-Reward Environments","created":"2021-03-08","cited_by_count":37,"area":null},{"id":"2211.08714","title":"Reward Gaming in Conditional Text Generation","created":"2022-11-16","cited_by_count":30,"area":null},{"id":"2301.04741","title":"Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models","created":"2023-01-11","cited_by_count":21,"area":null},{"id":"2206.09546","title":"Policy Optimization with Linear Temporal Logic Constraints","created":"2022-06-20","cited_by_count":19,"area":null},{"id":"2303.02135","title":"Eventual Discounting Temporal Logic Counterfactual Experience Replay","created":"2023-03-03","cited_by_count":19,"area":null},{"id":"2201.07082","title":"Inducing Structure in Reward Learning by Learning Features","created":"2022-01-18","cited_by_count":16,"area":null},{"id":"2402.00854","title":"SymbolicAI: A framework for logic-based approaches combining generative models and solvers","created":"2024-02-01","cited_by_count":16,"area":null},{"id":"2408.00418","title":"Towards Reliable Advertising Image Generation Using Human Feedback","created":"2024-08-01","cited_by_count":16,"area":null},{"id":"2304.08944","title":"Provably Feedback-Efficient Reinforcement Learning via Active Reward Learning","created":"2023-04-18","cited_by_count":15,"area":null},{"id":"2305.17400","title":"Query-Policy Misalignment in Preference-Based Reinforcement Learning","created":"2023-05-27","cited_by_count":15,"area":null},{"id":"2307.16348","title":"Rating-based Reinforcement Learning","created":"2023-07-30","cited_by_count":15,"area":null},{"id":"2309.15257","title":"STARC: A General Framework For Quantifying Differences Between Reward Functions","created":"2023-09-26","cited_by_count":15,"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":"2304.14177","title":"ChatGPT vs State-of-the-Art Models: A Benchmarking Study in Keyphrase Generation Task","created":"2023-04-27","cited_by_count":13,"area":null},{"id":"2311.01267","title":"UniFolding: Towards Sample-efficient, Scalable, and Generalizable Robotic Garment Folding","created":"2023-11-02","cited_by_count":13,"area":null},{"id":"2107.13507","title":"The Reasonable Crowd: Towards evidence-based and interpretable models of driving behavior","created":"2021-07-28","cited_by_count":12,"area":null},{"id":"2302.01928","title":"Aligning Robot and Human Representations","created":"2023-02-03","cited_by_count":11,"area":null},{"id":"2408.00170","title":"CREW: Facilitating Human-AI Teaming Research","created":"2024-07-31","cited_by_count":11,"area":null},{"id":"2410.10398","title":"Are LLMs Socially Adaptive? Contrasting Belief Evolution in Large Language Models and Humans","created":"2024-10-14","cited_by_count":11,"area":null},{"id":"2304.04602","title":"Learning a Universal Human Prior for Dexterous Manipulation from Human Preference","created":"2023-04-10","cited_by_count":10,"area":null},{"id":"2404.16779","title":"DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks","created":"2024-04-25","cited_by_count":10,"area":null},{"id":"2308.02435","title":"Designing Fiduciary Artificial Intelligence","created":"2023-07-27","cited_by_count":8,"area":null},{"id":"2312.02405","title":"BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks","created":"2023-12-05","cited_by_count":8,"area":null},{"id":"2312.11442","title":"Explore 3D Dance Generation via Reward Model from Automatically-Ranked Demonstrations","created":"2023-12-18","cited_by_count":8,"area":null},{"id":"2404.09445","title":"Exploring Text-to-Motion Generation with Human Preference","created":"2024-04-15","cited_by_count":8,"area":null},{"id":"2406.10942","title":"Effective Generative AI: The Human-Algorithm Centaur","created":"2024-06-16","cited_by_count":8,"area":null},{"id":"2110.14221","title":"Learning Diverse Policies in MOBA Games via Macro-Goals","created":"2021-10-27","cited_by_count":7,"area":null},{"id":"2302.03805","title":"Eliciting User Preferences for Personalized Multi-Objective Decision Making through Comparative Feedback","created":"2023-02-07","cited_by_count":7,"area":null},{"id":"2303.04562","title":"Extrapolative Controlled Sequence Generation via Iterative Refinement","created":"2023-03-08","cited_by_count":7,"area":null},{"id":"2505.10250","title":"ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization","created":"2025-05-15","cited_by_count":7,"area":null},{"id":"2202.02790","title":"Learning Synthetic Environments and Reward Networks for Reinforcement Learning","created":"2022-02-06","cited_by_count":6,"area":null},{"id":"2402.12907","title":"Roadmap on Incentive Compatibility for AI Alignment and Governance in Sociotechnical Systems","created":"2024-02-20","cited_by_count":6,"area":null},{"id":"2502.07237","title":"DrugImproverGPT: A Large Language Model for Drug Optimization with Fine-Tuning via Structured Policy Optimization","created":"2025-02-11","cited_by_count":6,"area":null},{"id":"2502.14581","title":"A Statistical Case Against Empirical Human-AI Alignment","created":"2025-02-20","cited_by_count":6,"area":null},{"id":"2104.03946","title":"Learning What To Do by Simulating the Past","created":"2021-04-08","cited_by_count":4,"area":null},{"id":"2104.10610","title":"Policy Fusion for Adaptive and Customizable Reinforcement Learning Agents","created":"2021-04-21","cited_by_count":4,"area":null},{"id":"2211.10861","title":"Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation","created":"2022-11-20","cited_by_count":4,"area":null},{"id":"2402.17527","title":"Predict the Next Word: Humans exhibit uncertainty in this task and language models _____","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2106.11345","title":"Cogment: Open Source Framework For Distributed Multi-actor Training, Deployment & Operations","created":"2021-06-21","cited_by_count":3,"area":null},{"id":"2407.04451","title":"Hindsight Preference Learning for Offline Preference-based Reinforcement Learning","created":"2024-07-05","cited_by_count":3,"area":null},{"id":"2410.01458","title":"From Reward Shaping to Q-Shaping: Achieving Unbiased Learning with LLM-Guided Knowledge","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2410.15181","title":"GUIDE: Real-Time Human-Shaped Agents","created":"2024-10-19","cited_by_count":3,"area":null},{"id":"2509.12049","title":"Interaction-Driven Browsing: A Human-in-the-Loop Conceptual Framework Informed by Human Web Browsing for Browser-Using Agents","created":"2025-09-15","cited_by_count":3,"area":null},{"id":"2112.01575","title":"Towards Interactive Reinforcement Learning with Intrinsic Feedback","created":"2021-12-02","cited_by_count":2,"area":null},{"id":"2202.10153","title":"Inferring Lexicographically-Ordered Rewards from Preferences","created":"2022-02-21","cited_by_count":2,"area":null},{"id":"2204.09622","title":"A Brief Guide to Designing and Evaluating Human-Centered Interactive Machine Learning","created":"2022-04-20","cited_by_count":2,"area":null},{"id":"2305.16621","title":"A Reminder of its Brittleness: Language Reward Shaping May Hinder Learning for Instruction Following Agents","created":"2023-05-26","cited_by_count":2,"area":null},{"id":"2307.12158","title":"DIP-RL: Demonstration-Inferred Preference Learning in Minecraft","created":"2023-07-22","cited_by_count":2,"area":null},{"id":"2309.16935","title":"TranDRL: A Transformer-Driven Deep Reinforcement Learning Enabled Prescriptive Maintenance Framework","created":"2023-09-29","cited_by_count":2,"area":null},{"id":"2312.14292","title":"Incorporating Human Flexibility through Reward Preferences in Human-AI Teaming","created":"2023-12-21","cited_by_count":2,"area":null},{"id":"2312.15160","title":"Human-AI Collaboration in Real-World Complex Environment with Reinforcement Learning","created":"2023-12-23","cited_by_count":2,"area":null},{"id":"2405.03341","title":"Enhancing Q-Learning with Large Language Model Heuristics","created":"2024-05-06","cited_by_count":2,"area":null},{"id":"2503.05306","title":"Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning","created":"2025-03-07","cited_by_count":2,"area":null},{"id":"2507.10995","title":"Misalignment from Treating Means as Ends","created":"2025-07-15","cited_by_count":2,"area":null},{"id":"2509.00841","title":"Neural Models and Language Model Prompting for the Multidimensional Evaluation of Open-Ended Conversations","created":"2025-08-31","cited_by_count":2,"area":null},{"id":"2602.05164","title":"Position: Capability Control Should be a Separate Goal From Alignment","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2103.12165","title":"Automated and Autonomous Experiment in Electron and Scanning Probe Microscopy","created":"2021-03-22","cited_by_count":1,"area":null},{"id":"2303.09027","title":"Learning Rewards to Optimize Global Performance Metrics in Deep Reinforcement Learning","created":"2023-03-16","cited_by_count":1,"area":null},{"id":"2304.03773","title":"Safe Explicable Planning","created":"2023-04-04","cited_by_count":1,"area":null},{"id":"2307.09692","title":"STRAPPER: Preference-based Reinforcement Learning via Self-training Augmentation and Peer Regularization","created":"2023-07-19","cited_by_count":1,"area":null},{"id":"2603.15017","title":"Consequentialist Objectives and Catastrophe","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2603.22813","title":"Learning What Matters Now: Dynamic Preference Inference under Contextual Shifts","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2604.28056","title":"RHyVE: Competence-Aware Verification and Phase-Aware Deployment for LLM-Generated Reward Hypotheses","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2307.12022","title":"Latent Utility Q-Learning for Preference-Adaptive Dynamic Treatment Regimes","created":"2023-07-22","cited_by_count":0,"area":null},{"id":"2311.12004","title":"Risk-averse Batch Active Inverse Reward Design","created":"2023-11-20","cited_by_count":0,"area":null},{"id":"2312.07624","title":"A dynamical clipping approach with task feedback for Proximal Policy Optimization","created":"2023-12-12","cited_by_count":0,"area":null},{"id":"2312.09865","title":"Automating reward function configuration for drug design","created":"2023-12-15","cited_by_count":0,"area":null},{"id":"2401.00330","title":"Two-Step Offline Preference-Based Reinforcement Learning with Constrained Actions","created":"2023-12-30","cited_by_count":0,"area":null},{"id":"2403.10160","title":"Online Policy Learning from Offline Preferences","created":"2024-03-15","cited_by_count":0,"area":null},{"id":"2409.18982","title":"Aligning Robot Navigation Behaviors with Human Intentions and Preferences","created":"2024-09-16","cited_by_count":0,"area":null},{"id":"2410.21882","title":"Building Altruistic and Moral AI Agent with Brain-inspired Emotional Empathy Mechanisms","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2410.22690","title":"Choice Between Partial Trajectories: Disentangling Goals from Beliefs","created":"2024-10-30","cited_by_count":0,"area":null},{"id":"2501.06376","title":"Robustness in the Face of Partial Identifiability in Reward Learning","created":"2025-01-10","cited_by_count":0,"area":null},{"id":"2602.15206","title":"MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2604.02349","title":"OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2605.23562","title":"ARMS: Automatic Reward Shaping for Sparse-Reward Multi-Agent Reinforcement Learning","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.16914","title":"Greed Is Learned: Visible Incentives as Reward-Hacking Triggers","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.17935","title":"DeLIVeR: Decomposed Learning for Information-grounded Veracity Recognition via Reinforced Knowledge Graph Exploration","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.08604","title":"Multi-Agent Reinforcement Learning via Agent-Specific Preference","created":"2026-08-09","cited_by_count":0,"area":null}],"next_cursor":null}