Near-optimal Reinforcement Learning using Bayesian Quantiles.
Aristide C. Y. TossouDebabrota BasuChristos DimitrakakisPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- function approximation
- posterior probability
- reinforcement learning algorithms
- bayesian inference
- multi agent
- bayesian estimation
- order statistics
- bayesian learning
- temporal difference
- bayesian networks
- multi agent reinforcement learning
- data distribution
- learning algorithm
- state space
- data driven
- maximum likelihood
- binary classification
- optimal control
- markov decision processes
- heavy hitters
- model free
- action selection
- optimal policy
- sliding window
- fixed size
- monte carlo
- dynamic programming
- function approximators
- temporal difference learning
- reinforcement learning methods
- robotic control