Asynchronous Reinforcement Learning for Real-Time Control of Physical Robots.
Yufeng YuanA. Rupam MahmoodPublished in: ICRA (2022)
Keyphrases
- real time control
- reinforcement learning
- control system
- real robot
- robotic control
- robot control
- mobile robot
- physical constraints
- function approximation
- flexible manufacturing systems
- autonomous robots
- multi robot
- physical objects
- learning algorithm
- human robot interaction
- robotic agents
- cooperative
- state space
- formation control
- reinforcement learning algorithms
- machining processes
- humanoid robot
- strong robustness
- multiple robots
- dynamic programming
- optimal policy
- closed loop
- robotic systems
- temporal difference
- model free
- real world
- markov decision processes
- reinforcement learning methods
- robust stability
- stability criterion
- multi agent
- optimal control