GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropy.
Tianhao PengWenjun WuHaitao YuanZhifeng BaoZhao PengruiXin YuXuetao LinYu LiangYanjun PuPublished in: CoRR (2023)
Keyphrases
- relative entropy
- neural network
- reinforcement learning
- information theoretic
- log likelihood
- information theory
- mutual information
- covariance matrix
- bregman divergences
- mahalanobis distance
- squared euclidean distance
- learning algorithm
- optimal policy
- maximum entropy
- multi class
- state space
- kullback leibler divergence
- special case
- feature vectors
- machine learning