Learning to Communicate with Reinforcement Learning for an Adaptive Traffic Control System.
Simon VannesteGauthier de BorrekensStig BosmansAstrid VannesteKevin MetsSiegfried MercelisSteven LatréPeter HellinckxPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- control system
- learning process
- learning algorithm
- learning problems
- online learning
- supervised learning
- prior knowledge
- learning tasks
- real time
- adaptive learning
- active learning
- wireless sensor networks
- dynamic programming
- state space
- knowledge acquisition
- markov decision processes
- learning capabilities
- robot control
- temporal difference learning
- autonomous learning
- policy search