Manipulator Motion Planning via Centralized Training and Decentralized Execution Multi-Agent Reinforcement Learning.
Yuliu WangRyusuke SagawaPublished in: ICARM (2022)
Keyphrases
- motion planning
- multi agent reinforcement learning
- degrees of freedom
- inverse kinematics
- robotic arm
- path planning
- multi agent
- robot arm
- trajectory planning
- mobile robot
- end effector
- humanoid robot
- configuration space
- cooperative
- robotic tasks
- robot manipulators
- multi agent learning
- multi robot
- control law
- stochastic games
- learning agents
- climbing robot
- collision free
- reinforcement learning
- multi agent systems
- distributed control
- dynamic environments