Empty nodes affect conditional cooperation under reinforcement learning.
Danyang JiaTong LiYang ZhaoXiaoqin ZhangZhen WangPublished in: Appl. Math. Comput. (2022)
Keyphrases
- reinforcement learning
- multi agent
- cooperative
- function approximation
- random field model
- graph structure
- temporal difference
- model free
- multi agent systems
- learning process
- state space
- optimal policy
- machine learning
- learning problems
- shortest path
- supervised learning
- data sets
- information sharing
- network structure
- social networks
- optimal control
- learning algorithm
- genetic algorithm
- temporal difference learning
- policy search