Leveraging Locality to Boost Sample Efficiency in Robotic Manipulation

Tong Zhang, Yingdong Hu, Jiacheng You, Yang Gao
Proceedings of The 8th Conference on Robot Learning, PMLR 270:3264-3284, 2025.

Abstract

Given the high cost of collecting robotic data in the real world, sample efficiency is a consistently compelling pursuit in robotics. In this paper, we introduce SGRv2, an imitation learning framework that enhances sample efficiency through improved visual and action representations. Central to the design of SGRv2 is the incorporation of a critical inductive bias—action locality, which posits that robot’s actions are predominantly influenced by the target object and its interactions with the local environment. Extensive experiments in both simulated and real-world settings demonstrate that action locality is essential for boosting sample efficiency. SGRv2 excels in RLBench tasks with keyframe control using merely 5 demonstrations and surpasses the RVT baseline in 23 of 26 tasks. Furthermore, when evaluated on ManiSkill2 and MimicGen using dense control, SGRv2’s success rate is 2.54 times that of SGR. In real-world environments, with only eight demonstrations, SGRv2 can perform a variety of tasks at a markedly higher success rate compared to baseline models.

Cite this Paper


BibTeX
@InProceedings{pmlr-v270-zhang25h, title = {Leveraging Locality to Boost Sample Efficiency in Robotic Manipulation}, author = {Zhang, Tong and Hu, Yingdong and You, Jiacheng and Gao, Yang}, booktitle = {Proceedings of The 8th Conference on Robot Learning}, pages = {3264--3284}, year = {2025}, editor = {Agrawal, Pulkit and Kroemer, Oliver and Burgard, Wolfram}, volume = {270}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v270/main/assets/zhang25h/zhang25h.pdf}, url = {https://proceedings.mlr.press/v270/zhang25h.html}, abstract = {Given the high cost of collecting robotic data in the real world, sample efficiency is a consistently compelling pursuit in robotics. In this paper, we introduce SGRv2, an imitation learning framework that enhances sample efficiency through improved visual and action representations. Central to the design of SGRv2 is the incorporation of a critical inductive bias—$\textit{action locality}$, which posits that robot’s actions are predominantly influenced by the target object and its interactions with the local environment. Extensive experiments in both simulated and real-world settings demonstrate that action locality is essential for boosting sample efficiency. SGRv2 excels in RLBench tasks with keyframe control using merely 5 demonstrations and surpasses the RVT baseline in 23 of 26 tasks. Furthermore, when evaluated on ManiSkill2 and MimicGen using dense control, SGRv2’s success rate is 2.54 times that of SGR. In real-world environments, with only eight demonstrations, SGRv2 can perform a variety of tasks at a markedly higher success rate compared to baseline models.} }
Endnote
%0 Conference Paper %T Leveraging Locality to Boost Sample Efficiency in Robotic Manipulation %A Tong Zhang %A Yingdong Hu %A Jiacheng You %A Yang Gao %B Proceedings of The 8th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2025 %E Pulkit Agrawal %E Oliver Kroemer %E Wolfram Burgard %F pmlr-v270-zhang25h %I PMLR %P 3264--3284 %U https://proceedings.mlr.press/v270/zhang25h.html %V 270 %X Given the high cost of collecting robotic data in the real world, sample efficiency is a consistently compelling pursuit in robotics. In this paper, we introduce SGRv2, an imitation learning framework that enhances sample efficiency through improved visual and action representations. Central to the design of SGRv2 is the incorporation of a critical inductive bias—$\textit{action locality}$, which posits that robot’s actions are predominantly influenced by the target object and its interactions with the local environment. Extensive experiments in both simulated and real-world settings demonstrate that action locality is essential for boosting sample efficiency. SGRv2 excels in RLBench tasks with keyframe control using merely 5 demonstrations and surpasses the RVT baseline in 23 of 26 tasks. Furthermore, when evaluated on ManiSkill2 and MimicGen using dense control, SGRv2’s success rate is 2.54 times that of SGR. In real-world environments, with only eight demonstrations, SGRv2 can perform a variety of tasks at a markedly higher success rate compared to baseline models.
APA
Zhang, T., Hu, Y., You, J. & Gao, Y.. (2025). Leveraging Locality to Boost Sample Efficiency in Robotic Manipulation. Proceedings of The 8th Conference on Robot Learning, in Proceedings of Machine Learning Research 270:3264-3284 Available from https://proceedings.mlr.press/v270/zhang25h.html.

Related Material