Kernel-Based Direct Policy Search Reinforcement Learning Based on Variational Bayesian Inference.
Nobuhiko YamaguchiOsamu FukudaHiroshi OkumuraPublished in: CANDAR Workshops (2019)
Keyphrases
- direct policy search
- variational bayesian inference
- reinforcement learning
- bayesian analysis
- latent dirichlet allocation
- state space
- mountain car
- kernel methods
- topic models
- support vector
- support vector machine
- learning algorithm
- markov decision processes
- machine learning
- function approximation
- model free
- action selection
- model selection