mlsanityData to 7 Oct 2026

Asking Easy Questions: A User-Friendly Approach to Active Reward Learning

arXiv 1910.04365 ↗First posted 10 Oct 2019cs.RO cs.AI cs.LGcited by 67

Not on the map. Why?

Cited by 22 in LLM alignment / RLHF / preference optimisation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Robots can learn the right reward function by querying a human expert. Existing approaches attempt to choose questions where the robot is most uncertain about the human's response; however, they do not consider how easy it will be for the human to answer! In this paper we explore an information gain formulation for optimally selecting questions that naturally account for the human's ability to answer. Our approach identifies questions that optimize the trade-off between robot and human uncertainty, and determines when these questions become redundant or costly. Simulations and a user study show our method not only produces easy questions, but also ultimately results in faster reward learning.

Key facts. Cited by 67 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 2; 2021: 10; 2022: 3; 2023: 18; 2024: 17; 2025: 7; 2026: 10.

67 papers.

Sort:

By area:

  1. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 743
  2. 2023Cognitive Architectures for Language Agentscited by 422
  3. 2024RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedbackcited by 147
  4. 2024Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learningcited by 147
  5. 2023RoboCLIP: One Demonstration is Enough to Learn Robot Policiescited by 128
  6. 2021ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learningcited by 98
  7. 2020Safe Imitation Learning via Fast Bayesian Reward Inference from Preferencescited by 73
  8. 2023Data Quality in Imitation Learningcited by 72
  9. 2020Active Preference-Based Gaussian Process Regression for Reward Learningcited by 70
  10. 2021LazyDAgger: Reducing Context Switching in Interactive Imitation Learningcited by 50
  11. 2021Learning Multimodal Rewards from Rankingscited by 41
  12. 2024Reinforcement Learning from Human Feedback with Active Queriescited by 39
38 more
  1. 2021Information Directed Reward Learning for Reinforcement Learningcited by 24
  2. 2021Learning Reward Functions from Scale Feedbackcited by 24
  3. 2023Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Modelscited by 20
  4. 2024Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedbackcited by 20
  5. 2023Provably Feedback-Efficient Reinforcement Learning via Active Reward Learningcited by 15
  6. 2023RLHF-Blender: A Configurable Interactive Interface for Learning from Diverse Human Feedbackcited by 15
  7. 2021APReL: A Library for Active Preference-based Reward Learning Algorithmscited by 14
  8. 2023Rating-based Reinforcement Learningcited by 14
  9. 2023Active Reward Learning from Multiple Teacherscited by 13
  10. 2023Active Reward Learning from Online Preferencescited by 12
  11. 2022Interactively Learning Preference Constraints in Linear Banditscited by 11
  12. 2021Uncertain Decisions Facilitate Better Preference Learningcited by 10
  13. 2021Preference-based Learning of Reward Function Featurescited by 9
  14. 2022Time-Efficient Reward Learning via Visually Assisted Cluster Rankingcited by 8
  15. 2024Batch Active Learning of Reward Functions from Human Preferencescited by 8
  16. 2024Navigating Noisy Feedback: Enhancing Reinforcement Learning with Error-Prone Language Modelscited by 7
  17. 2024MAPLE: A Framework for Active Preference Learning Guided by Large Language Modelscited by 6
  18. 2023Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarizationcited by 5
  19. 2023Online Decision Mediationcited by 4
  20. 2021Incentivizing Efficient Equilibria in Traffic Networks with Mixed Autonomycited by 3
  21. 2021Explaining Reward Functions to Humans for Better Human-Robot Collaborationcited by 3
  22. 2022Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learningcited by 3
  23. 2024Preferential Multi-Objective Bayesian Optimizationcited by 3
  24. 2024Preference Elicitation for Offline Reinforcement Learningcited by 3
  25. 2025Contrastive Learning from Exploratory Actions: Leveraging Natural Interactions for Preference Elicitationcited by 3
  26. 2025Open-Ended Goal Inference through Actions and Language for Human-Robot Collaborationcited by 3
  27. 2023DIP-RL: Demonstration-Inferred Preference Learning in Minecraftcited by 2
  28. 2024Reward Learning from Suboptimal Demonstrations with Applications in Surgical Electrocauterycited by 2
  29. 2025Interactive Multi-Objective Probabilistic Preference Learning with Soft and Hard Boundscited by 2
  30. 2026Causally Robust Reward Learning from Reason-Augmented Preference Feedbackcited by 2
  31. 2023On the Perception of Difficulty: Differences between Humans and AIcited by 1
  32. 2023A Markovian Formalism for Active Queryingcited by 1
  33. 2023Active Inverse Learning in Stackelberg Trajectory Gamescited by 1
  34. 2024A Generalized Acquisition Function for Preference-based Reward Learningcited by 1
  35. 2024FARPLS: A Feature-Augmented Robot Trajectory Preference Labeling System to Assist Human Labelers' Preference Elicitationcited by 1
  36. 2024Exploring and Addressing Reward Confusion in Offline Preference Learningcited by 1
  37. 2024Reactive Multi-Robot Navigation in Outdoor Environments Through Uncertainty-Aware Active Learning of Human Preference Landscapecited by 1
  38. 2024Demonstration Based Explainable AI for Learning from Demonstration Methodscited by 1

50 most cited of 67 All 67 (JSON)