Synchronous n-Step Method for Independent Q-Learning in Multi-Agent Deep Reinforcement Learning.
Xudong GongBo DingJie XuHuaimin WangXing ZhouHongda JiaPublished in: SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI (2019)
Keyphrases
- reinforcement learning
- multi agent
- high accuracy
- dynamic programming
- model free
- state space
- detection method
- significant improvement
- preprocessing
- computational complexity
- cooperative
- objective function
- pairwise
- learning algorithm
- multi agent systems
- multiagent systems
- function approximation
- optimal control
- function approximators