Randomised Bayesian Least-Squares Policy Iteration.
Nikolaos TziortziotisChristos DimitrakakisMichalis VazirgiannisPublished in: CoRR (2019)
Keyphrases
- temporal difference
- bayesian networks
- posterior probability
- bayesian learning
- data driven
- policy iteration
- model free
- gaussian processes
- bayesian analysis
- reinforcement learning methods
- data sets
- search procedure
- maximum likelihood
- reinforcement learning algorithms
- bayesian inference
- bayesian estimation
- reinforcement learning
- finite sample
- learning algorithm