APReL: A Library for Active Preference-based Reward Learning Algorithms. (arXiv:2108.07259v2 [cs.LG] UPDATED)

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 …

algorithms arxiv learning library