A Reinforcement Learning-based solution for Intra-domain Egress Selection.
Duc-Huy LeHai Anh TranSami SouihiPublished in: HPSR (2021)
Keyphrases
- reinforcement learning
- function approximation
- complex domains
- closed form
- data mining
- reinforcement learning algorithms
- markov decision processes
- domain independent
- transfer learning
- domain specific
- machine learning
- supervised learning
- mobile robot
- multi objective
- multi agent
- learning algorithm
- optimal control
- exact solution
- neural network
- learned knowledge
- robotic control