MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization.
Yongsheng MeiHanhan ZhouTian LanGuru VenkataramaniPeng WeiPublished in: AAMAS (2023)
Keyphrases
- multi agent
- optimization method
- cooperative
- optimization process
- optimization algorithm
- data sets
- real time
- search engine
- cooperative agents
- constrained optimization
- multi agent systems
- team formation
- discrete optimization
- optimization methods
- global optimization
- autonomous agents
- multiagent systems
- operating system
- optimization problems
- reinforcement learning
- case study
- information systems
- neural network