Scaling Reinforcement Learning to Robotics by Exploiting the Subsumption Architecture.
Sridhar MahadevanJonathan ConnellPublished in: ML (1991)
Keyphrases
- subsumption architecture
- robot control
- reinforcement learning
- mobile robot
- autonomous robots
- function approximation
- multi agent
- computer vision
- dynamic programming
- artificial intelligence
- model free
- data fusion
- robotic systems
- pid controller
- multi agent systems
- reinforcement learning algorithms
- autonomous navigation
- perception action