基于KL散度的策略优化 (KL-divergence-based Policy Optimization).
Jianguo LiHaitao ZhaoShaoyuan SunPublished in: 计算机科学 (2019)
Keyphrases
- kl divergence
- kullback leibler
- kullback leibler divergence
- mahalanobis distance
- information theoretic
- gaussian mixture
- gaussian distribution
- exponential family
- dissimilarity measure
- posterior distribution
- cross entropy
- probability density
- probabilistic latent semantic analysis
- closed form
- optimization procedure
- log likelihood
- distance measure
- optimization method
- euclidean distance