Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning
Zheng Wu,Yichen Xie,Wenzhao Lian,Changhao Wang,Yanjiang Guo,Jianyu Chen,Stefan Schaal,Masayoshi Tomizuka,Zheng Wu,Yichen Xie,Wenzhao Lian,Changhao Wang,Yanjiang Guo,Jianyu Chen,Stefan Schaal,Masayoshi Tomizuka
Humans are capable of abstracting various tasks as different combinations of multiple attributes. This perspective of compositionality is vital for human rapid learning and adaption since previous experiences from related tasks can be combined to generalize across novel compositional settings. In this work, we aim to achieve zero-shot policy generalization of Reinforcement Learning (RL) agents by ...
