Distributional reinforcement learning with epistemic and aleatoric uncertainty estimation.
Qi LiuYanjie LiShiyu ChenKe LinXiongtao ShiYunjiang LouPublished in: Inf. Sci. (2023)
Keyphrases
- reinforcement learning
- optimal policy
- learning algorithm
- partial observability
- state space
- accurate estimation
- function approximation
- neural network
- estimation accuracy
- density estimation
- temporal difference
- model free
- inherent uncertainty
- data sets
- semi parametric
- reinforcement learning algorithms
- robust estimation
- uncertain data
- transfer learning
- co occurrence
- dynamic programming
- multi agent
- machine learning