Staged Reinforcement Learning for Complex Tasks Through Decomposed Environments.
Rafael PinaCorentin ArtaudXiaolan LiuVaruna De SilvaPublished in: ISPR (2) (2023)
Keyphrases
- reinforcement learning
- real world
- highly dynamic
- complex environments
- complex systems
- complex data
- complex domains
- function approximation
- robotic systems
- high level
- uncertain environments
- multi agent environments
- decision making
- reinforcement learning algorithms
- robotic control
- real world environments
- adaptation process
- temporal abstractions
- real robot
- genetic algorithm
- supervised learning
- model free
- multi agent
- database
- learning process
- dynamic programming
- dynamic environments