Modelling uncertainty in reinforcement learning.
Ryan W. MurrayMichele PalladinoPublished in: CDC (2019)
Keyphrases
- reinforcement learning
- function approximation
- partial observability
- reinforcement learning algorithms
- belief functions
- markov decision processes
- machine learning
- model free
- uncertain data
- optimal policy
- dynamic programming
- artificial intelligence
- learning problems
- optimal control
- multi agent
- decision theory
- temporal difference
- learning algorithm
- real world
- inherent uncertainty
- robotic control