Keyphrases
- reinforcement learning
- partial observability
- uncertain data
- machine learning
- inherent uncertainty
- function approximation
- real world
- sequential decision problems
- reinforcement learning algorithms
- optimal policy
- state space
- neural network
- incomplete information
- conditional probabilities
- dynamic programming
- active learning
- decision theory
- learning process
- possibility theory
- function approximators
- learning environment
- learning algorithm