Direct Uncertainty Estimation in Reinforcement Learning.
Sergey RodionovAlexey PotapovYurii VinogradovPublished in: CoRR (2013)
Keyphrases
- reinforcement learning
- learning algorithm
- partial observability
- model free
- multi agent
- accurate estimation
- learning problems
- temporal difference
- learning process
- state space
- real time
- estimation error
- density estimation
- policy search
- autonomous learning
- estimation algorithm
- optimal control
- function approximation
- uncertain data
- supervised learning
- data sets