On Stochastic Optimal Control and Reinforcement Learning by Approximate Inference (Extended Abstract).
Konrad RawlikMarc ToussaintSethu VijayakumarPublished in: IJCAI (2013)
Keyphrases
- extended abstract
- approximate inference
- reinforcement learning
- graphical models
- belief propagation
- probabilistic inference
- gaussian process
- variational methods
- parameter estimation
- message passing
- exact inference
- bayesian networks
- loopy belief propagation
- latent variables
- dynamic bayesian networks
- factor graphs
- conditional random fields
- machine learning
- expectation propagation
- learning algorithm
- markov random field
- probabilistic model
- structured prediction
- state space
- free energy
- support vector
- random variables
- graph cuts
- super resolution
- information extraction
- hidden markov models
- image processing