Reachability-Based Trajectory Safeguard (RTS): A Safe and Fast Reinforcement Learning Safety Layer for Continuous Control.
Yifei Simon ShaoChen ChaoShreyas KousikRam VasudevanPublished in: IEEE Robotics Autom. Lett. (2021)
Keyphrases
- reinforcement learning
- state space
- control problems
- optimal control
- control strategies
- robot control
- spatio temporal
- function approximation
- control theory
- continuous domains
- action selection
- multi layer
- control system
- machine learning
- robotic control
- robot motion
- action space
- upper layer
- real time
- reinforcement learning algorithms
- markov decision processes
- dynamic programming
- neural network