Multi-Agent Collaboration via Reward Attribution Decomposition.
Tianjun ZhangHuazhe XuXiaolong WangYi WuKurt KeutzerJoseph E. GonzalezYuandong TianPublished in: CoRR (2020)
Keyphrases
- multi agent
- reinforcement learning
- multi agent systems
- intelligent agents
- decomposition method
- multiagent systems
- cooperative
- information sharing
- collaborative environment
- software agents
- collaborative learning
- team formation
- multi agent coordination
- collective intelligence
- multi agent architecture
- cooperative agents
- heterogeneous agents
- cross disciplinary
- multiple perspectives
- oriented programming
- single agent
- reward function
- multiple agents
- neural network
- markov decision processes
- autonomous agents
- knowledge management
- decision making