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

2021/08/16 by Erdem Bıyık, Bıyık, Erdem, Aditi Talati +3
Computer Science · #Advanced Database Systems and Queries #Artificial Intelligence (cs.AI) #Data Management and Algorithms #FOS: Computer and information sciences #Logic, Reasoning, and Knowledge #Machine Learning (cs.LG) #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.2108.07259

openalex publication_date 2021/08/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Related

• Batch Active Preference-Based Learning of Reward Functions
• Active Reward Learning from Online Preferences
• Batch Active Learning of Reward Functions from Human Preferences
• A Generalized Acquisition Function for Preference-based Reward Learning
• Learning Reward Functions from Diverse Sources of Human Feedback: Optimally Integrating Demonstrations and Preferences