Run Time Assured Reinforcement Learning for Safe Satellite Docking.
Kyle DunlapMark MoteKaiden DelsingKerianne L. HobbsPublished in: J. Aerosp. Inf. Syst. (2023)
Keyphrases
- reinforcement learning
- function approximation
- remote sensing
- robotic control
- machine learning
- reinforcement learning algorithms
- state space
- markov decision processes
- model free
- learning process
- database
- real robot
- learning classifier systems
- learning agents
- temporal difference learning
- transition model
- orbit determination
- direct policy search
- control problems
- temporal difference
- action selection
- learning problems
- optimal policy
- supervised learning
- data mining