Traffic Signal Control: a Double Q-learning Approach.
Anton AgafonovVladislav V. MyasnikovPublished in: FedCSIS (2021)
Keyphrases
- traffic signal control
- traffic signal
- reinforcement learning
- traffic control
- cooperative
- traffic congestion
- multi agent
- state space
- multi agent systems
- learning algorithm
- traffic light
- control policy
- traffic management
- traffic flows
- traffic flow
- machine learning
- shortest path
- optimal policy
- markov decision processes
- long run
- multi objective
- control system
- search space