Nonparametric Bayesian Policy Priors for Reinforcement Learning.
Finale Doshi-VelezDavid WingateNicholas RoyJoshua B. TenenbaumPublished in: NIPS (2010)
Keyphrases
- nonparametric bayesian
- reinforcement learning
- optimal policy
- dirichlet process
- mixture modeling
- statistical modeling
- mixture model
- multi task learning
- gaussian processes
- bayesian model
- state space
- dynamic programming
- bayesian framework
- transfer learning
- posterior distribution
- variational methods
- unsupervised learning
- latent topics
- co occurrence
- prior information
- gaussian process
- learning problems
- machine learning algorithms
- model selection
- semi supervised