Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence.
Lingwei ZhuZheng ChenTakamitsu MatsubaraMartha WhitePublished in: CoRR (2023)
Keyphrases
- kl divergence
- reinforcement learning
- kullback leibler divergence
- information theoretic
- information theory
- kullback leibler
- mahalanobis distance
- gaussian mixture
- gaussian distribution
- machine learning
- mutual information
- posterior distribution
- state space
- exponential family
- distance measure
- probabilistic model
- latent variables
- log likelihood
- probabilistic latent semantic analysis