Extend Single-agent Reinforcement Learning Approach to a Multi-robot Cooperative Task in an Unknown Dynamic Environment.
Ying WangClarence W. de SilvaPublished in: IJCNN (2006)
Keyphrases
- dynamic environments
- single agent
- multi robot cooperative
- reinforcement learning
- action space
- path planning
- multi robot
- multi agent environments
- multiple robots
- learning agent
- autonomous agents
- reinforcement learning algorithms
- mobile robot
- multi agent
- plan execution
- policy gradient
- collision free
- autonomous navigation
- state space
- search strategies
- markov decision processes
- machine learning