DyPS: Dynamic Parameter Sharing in Multi-Agent Reinforcement Learning for Spatio-Temporal Resource Allocation.
Jingwei WangQianyue HaoWenzhen HuangXiaochen FanZhentao TangBin WangJianye HaoYong LiPublished in: KDD (2024)
Keyphrases
- resource allocation
- multi agent reinforcement learning
- spatio temporal
- dynamic resource allocation
- resource management
- resource allocation problems
- resource availability
- optimal resource allocation
- allocation problems
- scarce resources
- distributed resource allocation
- artificial intelligence
- multi agent learning
- resource allocation decisions
- game theory
- cooperative
- learning agents
- information sharing
- dynamic environments