Behavior Transformers: Cloning $k$ modes with one stone. (arXiv:2206.11251v2 [cs.LG] UPDATED)

While behavior learning has made impressive progress in recent times, it lags
behind computer vision and natural language processing due to its inability to
leverage large, human-generated datasets. Human behaviors have wide variance,
multiple modes, and human demonstrations typically do not come with reward
labels. These properties limit the applicability of current methods in Offline
RL and Behavioral Cloning to learn from large, pre-collected datasets. In this
work, we present Behavior Transformer (BeT), a new technique to model unlabeled
demonstration …

arxiv behavior cloning transformers