Adaptive Multi-robot Team Reconfiguration Using a Policy-Reuse Reinforcement Learning Approach.
Prithviraj DasguptaKe ChengBikramjit BanerjeePublished in: AAMAS Workshops (2011)
Keyphrases
- multi robot
- robot soccer
- action selection
- multi robot exploration
- reinforcement learning
- multi robot coordination
- search and rescue
- optimal policy
- robot teams
- path planning
- real robot
- mobile robot
- multi robot systems
- policy search
- actor critic
- multiple robots
- function approximation
- potential field
- temporal difference
- function approximators
- multi robot cooperative
- robotic systems
- dynamic programming
- uncertain environments
- partially observable
- reinforcement learning algorithms
- markov decision process
- policy gradient
- model free
- motion planning
- formation control
- state space
- image sequences
- multi agent
- video sequences
- dynamic environments
- markov decision processes
- surveillance system
- infinite horizon
- action space
- machine learning