Effect of Virtual Work Braking on Distributed Multi-robot Reinforcement Learning.
Hiroshi KawanoPublished in: SMC (2013)
Keyphrases
- multi robot
- distributed architecture
- reinforcement learning
- robot teams
- multi robot coordination
- multiple robots
- real robot
- path planning
- mobile robot
- multi robot systems
- multi robot exploration
- multi agent
- potential field
- dynamic task allocation
- state space
- cooperative
- motion planning
- search and rescue
- multi robot cooperative
- robot soccer
- robotic systems
- machine learning
- coalitional game theory
- initially unknown
- uncertain environments
- action selection
- surveillance system
- optimal policy
- feature vectors
- image sequences
- computer vision
- genetic algorithm