Tutorial and Survey on Probabilistic Graphical Model and Variational Inference in Deep Reinforcement Learning

Probabilistic Graphical Models and Variational Inference play an important role in recent advances in Deep Reinforcement Learning. As a self-inclusive tutorial survey, this article illustrates basic concepts of reinforcement learning with Probabilistic Graphical Models and offers derivation of some basic formula as a recap. Reviews and comparisons on recent advances in deep reinforcement learning are made from various aspects. We offer Probabilistic Graphical Models, detailed explanation and derivation to several use cases of Graphical Model and Variational Inference, which serves as a complementary material on top of the original contributions.