A Review of Uncertainty for Deep Reinforcement Learning.
Owen LockwoodMei SiPublished in: AIIDE (2022)
Keyphrases
- reinforcement learning
- function approximation
- partial observability
- uncertain data
- sequential decision problems
- robotic control
- dynamic programming
- temporal difference
- machine learning
- function approximators
- reinforcement learning algorithms
- model free
- utility function
- learning algorithm
- decision problems
- optimal control
- belief functions
- literature review
- decision theory
- state space
- probability distribution
- partially observable
- evolutionary algorithm
- temporal difference learning
- multi agent
- relevant literature
- inherent uncertainty
- data sets