Real-Time Lane Configuration with Coordinated Reinforcement Learning.
Udesh GunarathnaHairuo XieEgemen TaninShanika KarunasekeraRenata Borovica-GajicPublished in: ECML/PKDD (4) (2020)
Keyphrases
- real time
- reinforcement learning
- robotic control
- multi agent
- function approximation
- low cost
- high speed
- optimal configuration
- real time systems
- vision system
- cooperative
- data sets
- state space
- dynamic programming
- optimal policy
- markov decision processes
- data acquisition
- reinforcement learning algorithms
- learning algorithm
- autonomous learning
- machine learning