SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning.
Jianhong WangYuan ZhangYunjie GuTae-Kyun KimPublished in: NeurIPS (2022)
Keyphrases
- multi agent
- reinforcement learning
- cooperative
- multi agent systems
- coalition formation
- single agent
- intelligent agents
- multiagent systems
- learning algorithm
- autonomous agents
- state space
- optimal policy
- software agents
- game theory
- function approximation
- game theoretic
- multiple agents
- machine learning
- von neumann
- heterogeneous agents
- team formation