Zero-shot Policy Learning with Spatial Temporal Reward Decomposition on Contingency-aware Observation

Huazhe Xu, Boyuan Chen, Yang Gao 0029, Trevor Darrell. Zero-shot Policy Learning with Spatial Temporal Reward Decomposition on Contingency-aware Observation. In IEEE International Conference on Robotics and Automation, ICRA 2021, Xi'an, China, May 30 - June 5, 2021. pages 10786-10792, IEEE, 2021. [doi]

Abstract

Abstract is missing.