UneVEn: Universal value exploration for multi-agent reinforcement learning
VDN and QMIX are two popular value-based algorithms for cooperative MARL that learn a centralized action value function as a monotonic mixing of per-agent utilities. While this enables easy decentralization of the learned policy, the restricted joint action value function can prevent them from solvi...
| Main Authors: | , , , , |
|---|---|
| 格式: | Conference item |
| 语言: | English |
| 出版: |
PMLR
2021
|