Distributed traffic light control at uncoupled intersections with real-world topology by deep reinforcement learning.
Mark SchuteraNiklas GobyStefan SmolarekMarkus ReischlPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- real world
- traffic light
- multi agent
- distributed systems
- distributed environment
- wide range
- markov decision processes
- learning algorithm
- cooperative
- neural network
- optimal policy
- peer to peer
- data sets
- data mining
- traffic control
- robot control
- topology preserving
- reinforcement learning algorithms
- mobile robot
- social networks