Multi-agent deep reinforcement learning for traffic signal control with Nash Equilibrium.
Wei WeiQiang WuJianqing WuBo DuJun ShenTinghong LiPublished in: HPCC/DSS/SmartCity/DependSys (2021)
Keyphrases
- traffic signal control
- nash equilibrium
- reinforcement learning
- game theory
- game theoretic
- multi agent
- worst case
- pure strategy
- stackelberg game
- mixed strategy
- regret minimization
- stochastic games
- nash equilibria
- multi agent systems
- traffic signal
- multi objective
- reinforcement learning algorithms
- solution concepts
- cooperative
- machine learning
- learning algorithm
- learning agents
- traffic congestion
- model free
- markov decision processes
- path planning
- np hard
- evolutionary algorithm