Learning to Communicate with Reinforcement Learning for an Adaptive Traffic Control System.
Simon VannesteGauthier de BorrekensStig BosmansAstrid VannesteKevin MetsSiegfried MercelisSteven LatréPeter HellinckxPublished in: 3PGCIC (2021)
Keyphrases
- reinforcement learning
- control system
- learning algorithm
- learning process
- learning systems
- learning problems
- learning capabilities
- reinforcement learning methods
- active learning
- multi agent
- supervised learning
- temporal difference learning
- prior knowledge
- machine learning
- mobile learning
- closed loop
- learning agent
- learning agents