Reinforcement learning of dual-arm cooperation for a mobile manipulator with sequences of dynamical movement primitives.
Mingdi DengYingbai HuZhijun LiPublished in: ICARM (2017)
Keyphrases
- reinforcement learning
- human arm
- multi agent
- cooperative
- function approximation
- hidden markov models
- state space
- movement patterns
- robotic arm
- motion planning
- building blocks
- low level
- optimal policy
- information sharing
- reinforcement learning algorithms
- high level
- temporal difference
- model free
- dynamical systems
- sequence alignment
- dynamic programming
- learning process
- learning algorithm
- optimal control
- markov decision processes
- machine learning
- virtual enterprise
- reinforcement learning methods