Nash double Q-based multi-agent deep reinforcement learning for interactive merging strategy in mixed traffic.
Lin LiWanzhong ZhaoChunyan WangAbbas FotouhiXuze LiuPublished in: Expert Syst. Appl. (2024)
Keyphrases
- reinforcement learning
- multi agent
- traffic signal control
- cooperative
- multi agent systems
- multi agent environments
- multiagent systems
- function approximation
- reinforcement learning agents
- exploration strategy
- reinforcement learning algorithms
- real time
- user interaction
- network traffic
- leader follower
- intelligent agents
- multi agent reinforcement learning
- learning agents
- multiple agents
- markov decision processes
- single agent
- social welfare
- utility function
- traffic control
- multiagent learning
- traffic flow
- autonomous agents
- state space
- learning algorithm