Outcome-Driven Reinforcement Learning via Variational Inference.
Tim G. J. RudnerVitchyr PongRowan McAllisterYarin GalSergey LevinePublished in: NeurIPS (2021)
Keyphrases
- variational inference
- reinforcement learning
- bayesian inference
- probabilistic model
- topic models
- posterior distribution
- latent dirichlet allocation
- probabilistic graphical models
- variational methods
- gaussian process
- mixture model
- closed form
- approximate inference
- exact inference
- exponential family
- graphical models
- factor graphs
- learning algorithm
- latent variables
- prior information
- state space
- machine learning
- density estimation
- belief networks
- generative model
- level set
- text mining