Direct Policy Search Reinforcement Learning Based on Variational Bayesian Inference.
Nobuhiko YamaguchiKazuya IharaOsamu FukudaHiroshi OkumuraPublished in: SCIS&ISIS (2018)
Keyphrases
- direct policy search
- variational bayesian inference
- reinforcement learning
- bayesian analysis
- latent dirichlet allocation
- topic models
- mountain car
- function approximation
- state space
- learning algorithm
- optimal policy
- data mining
- temporal difference
- markov decision processes
- collapsed gibbs sampling
- control problems
- transfer learning
- dynamic programming
- evolutionary algorithm
- machine learning