Batch Active Learning of Reward Functions from Human Preferences

arXiv:2402.15757v1 Announce Type: new
Abstract: Data generation and labeling are often expensive in robot learning. Preference-based learning is a concept that enables reliable labeling by querying users with preference questions. Active querying methods are commonly employed in preference-based learning to generate more informative data at the expense of parallelization and computation time. In this paper, we develop a set of novel algorithms, batch active preference-based learning methods, that enable efficient learning of reward functions using as few data samples as …

abstract active learning arxiv computation concept cs.ai cs.lg cs.ro data functions generate human labeling parallelization questions robot stat.ml type