Improving the speed of convergence of multi-agent Q-learning for cooperative task-planning by a robot-team.
Arup Kumar SadhuAmit KonarPublished in: Robotics Auton. Syst. (2017)
Keyphrases
- cooperative
- multi agent
- robot soccer
- action selection
- cooperating agents
- cooperative agents
- robot teams
- single agent
- heterogeneous agents
- reinforcement learning
- mobile robot
- multi agent systems
- goal directed
- motion planning
- team formation
- robotic soccer
- multiagent systems
- multi agent planning
- agent cooperation
- human robot interaction
- real time
- multi robot
- multi robot systems
- autonomous agents
- multi agent reinforcement learning
- navigation tasks
- action selection mechanism
- multi robot coordination
- collision free
- path planning
- planning problems
- intelligent agents
- convergence rate
- robotic systems
- multiple robots
- search and rescue
- multiple agents
- vision system
- heuristic search
- dynamic environments
- autonomous robots
- robot navigation
- real robot
- world model
- planning domains
- humanoid robot
- stochastic approximation
- formation control
- convergence proof
- robotic arm
- agent behavior
- blocks world