DOMINO: Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning

Yao Mu, Yuzheng Zhuang, Fei Ni, Bin Wang, Jianyu Chen, Jianye Hao, Ping Luo

被引用 10 次

摘要

According to the Barber and Agakov's variational lower bound [1], the mutual information I(x; y) between x and y can be bounded as follows: