Variational Bayesian Reinforcement Learning with Regret Bounds.
Brendan O'DonoghuePublished in: CoRR (2018)
Keyphrases
- variational bayesian
- reinforcement learning
- regret bounds
- matrix factorization
- exponential family
- expectation maximization
- incomplete data
- density function
- online learning
- lower bound
- state space
- transfer learning
- maximum likelihood
- machine learning
- markov random field
- least squares
- learning algorithm
- density estimation
- upper bound
- learning process