Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learning.
Bertrand CharpentierRansalu SenanayakeMykel J. KochenderferStephan GünnemannPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- partial observability
- multi agent
- uncertain data
- machine learning
- state space
- sequential decision problems
- inherent uncertainty
- action selection
- neural network
- robotic control
- optimal policy
- decision theory
- reinforcement learning algorithms
- markov decision process
- data sets
- conditional probabilities
- rough sets
- dynamic programming
- belief functions
- reinforcement learning methods
- stochastic approximation
- bayesian networks