Exponential Family Model-Based Reinforcement Learning via Score Matching.

Gene Li Junbo Li Anmol Kabra Nati Srebro Zhaoran Wang Zhuoran Yang

Published in: NeurIPS (2022)

Keyphrases

exponential family
model based reinforcement learning
log likelihood
maximum likelihood
graphical models
missing values
density estimation
mixture model
markov decision processes
closed form
statistical models
hidden variables
scoring function
variational methods
em algorithm
order statistics