Fundamental Limits of Reinforcement Learning in Environment with Endogeneous and Exogeneous Uncertainty.
Rongpeng LiPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- fundamental limits
- mobile robot
- learning algorithm
- function approximation
- learning process
- high quality
- image processing
- computing environments
- optimal control
- real robot
- partial knowledge
- partial observability
- image sequences
- multi agent
- dynamic programming
- belief functions
- probability theory
- computer vision