Timezone: »

 
Poster
Behavior Transformers: Cloning $k$ modes with one stone
Nur Muhammad Shafiullah · Zichen Cui · Ariuntuya (Arty) Altanzaya · Lerrel Pinto

Tue Nov 29 09:00 AM -- 11:00 AM (PST) @ Hall J #110
in Poster Session 1 »

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 behavior has a wide variance, multiple modes, and human demonstrations naturally 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 data with multiple modes. BeT retrofits standard transformer architectures with action discretization coupled with a multi-task action correction inspired by offset prediction in object detection. This allows us to leverage the multi-modal modeling ability of modern transformers to predict multi-modal continuous actions. We experimentally evaluate BeT on a variety of robotic manipulation and self-driving behavior datasets. We show that BeT significantly improves over prior state-of-the-art work on solving demonstrated tasks while capturing the major modes present in the pre-collected datasets. Finally, through an extensive ablation study, we further analyze the importance of every crucial component in BeT. Videos of behavior generated by BeT are available here: https://mahis.life/bet

Keywords: learning from demonstrations · behavioral cloning
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Nur Muhammad Shafiullah (New York University)

Trying to teach robots to do all my chores at New York University and FAIR.

Zichen Cui (New York University)
Ariuntuya (Arty) Altanzaya (New York University)
Lerrel Pinto (New York University)

More from the Same Authors