Скачать или смотреть Erdem Bıyık's Talk on "APReL: A Library for Active Preference-based Reward Learning Algorithms"

Erdem Bıyık's Talk at AI-HRI 2021 on the paper:
APReL: A Library for Active Preference-based Reward Learning Algorithms
Erdem Bıyık, Aditi Talati, Dorsa Sadigh
Artificial Intelligence for Human-Robot Interaction (AI-HRI) at AAAI Fall Symposium Series, November 2021

Paper: https://arxiv.org/abs/2108.07259
Web Site: https://aprel.readthedocs.io/en/latest/
Code: https://github.com/Stanford-ILIAD/APReL
Supplementary Video:    • APReL: A Library for Active Preference-bas...  

Abstract:
Reward learning is a fundamental problem in robotics 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.