Dueling Posterior Sampling for Preference-Based Reinforcement Learning.
Ellen R. NovosellerYanan SuiYisong YueJoel W. BurdickPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- markov chain monte carlo
- metropolis hastings
- sampling algorithm
- reinforcement learning algorithms
- random sampling
- function approximation
- probability distribution
- monte carlo
- machine learning
- data sets
- learning problems
- bayesian framework
- posterior probability
- robotic control
- state space
- markov decision processes
- multi agent
- posterior distribution
- action selection
- markov chain
- learning algorithm
- sampling methods
- class probabilities
- sampling strategy
- multi agent reinforcement learning
- sampling strategies
- parameter estimation
- optimal policy