mlsanityData to 7 Oct 2026

APReL: A Library for Active Preference-based Reward Learning Algorithms

arXiv 2108.07259 ↗First posted 16 Aug 2021cs.LG cs.AI cs.ROcited by 14

Not on the map. Why?

Abstract (arXiv)

Reward learning is a fundamental problem in human-robot interaction to have robots that operate in alignment with what their human user wants. Many preference-based learning algorithms and active querying techniques have been proposed as a solution to this problem. In this paper, we present APReL, a library for active preference-based reward learning algorithms, which enable researchers and practitioners to experiment with the existing techniques and easily develop their own algorithms for various modules of the problem. APReL is available at https://github.com/Stanford-ILIAD/APReL.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 19 of its 34 references that are in the map. First posted on arXiv 16 Aug 2021.

Builds on

19 of 34 references.

References · 19

  1. 2017Deep reinforcement learning from human preferencescited by 3,846
  2. 2016OpenAI Gymcited by 1,684
  3. 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 256
  4. 2017Third-Person Imitation Learningcited by 103
  5. 2018Batch Active Preference-Based Learning of Reward Functionscited by 87
  6. 2020Learning Reward Functions from Diverse Sources of Human Feedback: Optimally Integrating Demonstrations and Preferencescited by 71
  7. 2020Active Preference-Based Gaussian Process Regression for Reward Learningcited by 70
  8. 2019Asking Easy Questions: A User-Friendly Approach to Active Reward Learningcited by 67
  9. 2019Learning Reward Functions by Integrating Human Demonstrations and Preferencescited by 64
  10. 2019Batch Active Learning Using Determinantal Point Processescited by 42
  11. 2019Preference-Based Learning for Exoskeleton Gait Optimizationcited by 23
  12. 2020Active Preference Learning using Maximum Regretcited by 21
7 more
  1. 2021Learning Human Objectives from Sequences of Physical Correctionscited by 21
  2. 2020ROIAL: Region of Interest Active Learning for Characterizing Exoskeleton Gait Preference Landscapescited by 19
  3. 2019The Green Choice: Learning and Influencing Human Decisions on Shared Roadscited by 14
  4. 2019Learning an Urban Air Mobility Encounter Model from Expert Preferencescited by 12
  5. 2020Interactive Robot Training for Non-Markov Taskscited by 9
  6. 2021Preference-based Learning of Reward Function Featurescited by 9
  7. 2021Here's What I've Learned: Asking Questions that Reveal Reward Learningcited by 8

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 5; 2024: 5; 2025: 2.

14 papers.

Sort:

By area:

  1. 2022imitation: Clean Imitation Learning Implementationscited by 34
  2. 2024Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedbackcited by 20
  3. 2024Learning Reward for Robot Skills Using Large Language Models via Self-Alignmentcited by 19
  4. 2023RLHF-Blender: A Configurable Interactive Interface for Learning from Diverse Human Feedbackcited by 15
  5. 2023Rating-based Reinforcement Learningcited by 14
  6. 2021Interpretable Preference-based Reinforcement Learning with Tree-Structured Reward Functionscited by 10
  7. 2024Batch Active Learning of Reward Functions from Human Preferencescited by 8
  8. 2023Learning Reward for Physical Skills using Large Language Modelcited by 5
  9. 2023Optimizing Algorithms From Pairwise User Preferencescited by 3
  10. 2025Does Your AI Agent Get You? A Personalizable Framework for Approximating Human Models from Argumentation-based Dialogue Tracescited by 3
  11. 2023Predicting Human Perceptions of Robot Performance During Navigation Taskscited by 2
  12. 2025ProVox: Personalization and Proactive Planning for Situated Human-Robot Collaborationcited by 2
2 more
  1. 2024DP-Dueling: Learning from Preference Feedback without Compromising User Privacycited by 1
  2. 2024Cieran: Designing Sequential Colormaps via In-Situ Active Preference Learningcited by 0