Multi-Agent Meta-Reinforcement Learning with Coordination and Reward Shaping for Traffic Signal Control.
Xin DuJiahai WangSiyuan ChenPublished in: PAKDD (2) (2023)
Keyphrases
- traffic signal control
- reward shaping
- reinforcement learning
- multi agent
- reinforcement learning algorithms
- function approximation
- complex domains
- cooperative
- multi agent systems
- multiagent systems
- state space
- multiple agents
- learning algorithm
- temporal difference
- model free
- machine learning
- software agents
- autonomous agents
- intelligent agents
- optimal policy
- supervised learning
- markov decision problems
- traffic signal
- learning process
- optimal control
- dynamic programming
- action space
- function approximators