Settling the Variance of Multi-Agent Policy Gradients.
Jakub Grudzien KubaMuning WenLinghui MengShangding GuHaifeng ZhangDavid MguniJun WangYaodong YangPublished in: NeurIPS (2021)
Keyphrases
- multi agent
- optimal policy
- multi agent systems
- cooperative
- single agent
- intelligent agents
- multiple agents
- reinforcement learning
- partially observable markov decision processes
- autonomous agents
- infinite horizon
- machine learning
- policy makers
- variance reduction
- multi agent coordination
- software agents
- normal distribution
- intra class
- trade off
- asymptotically optimal
- gradient information
- minimum variance
- cooperative agents
- team formation
- multi agent based simulation