Bayesian Policy Gradients via Alpha Divergence Dropout Inference.
Peter HendersonThang DoanRiashat IslamDavid MegerPublished in: CoRR (2017)
Keyphrases
- bayesian inference
- bayesian networks
- markov chain monte carlo
- bayesian model
- probabilistic inference
- data driven
- inference process
- optimal policy
- bayesian learning
- bayesian models
- statistical inference
- maximum likelihood
- belief networks
- policy making
- allocation policy
- infinite horizon
- hyperparameters
- neural network
- random fields
- gibbs sampling
- markov decision process
- gradient information
- relative entropy
- variational inference
- probabilistic model
- belief nets
- bayesian decision