Simulating multi-exit evacuation using deep reinforcement learning.
Dong XuXiao HuangJoseph MangoXiang LiZhenlong LiPublished in: Trans. GIS (2021)
Keyphrases
- reinforcement learning
- multi agent
- cellular automata
- function approximation
- traffic flow
- learning algorithm
- neural network
- social networks
- learning process
- temporal difference
- state space
- supervised learning
- multi agent reinforcement learning
- deep learning
- optimal control
- transfer learning
- active learning
- search algorithm
- machine learning