很认真的中了两篇AAAI2020的文章：NCC-MARL: Neighborhood Cognition Consistent Multi-Agent Reinforcement Learning.

最新推荐文章于 2024-08-14 18:03:40 发布

mmc2015

最新推荐文章于 2024-08-14 18:03:40 发布

阅读量2.8k

点赞数 6

分类专栏：（深度）增强学习文章标签： MARL Multi-Agent Reinforcement Lear Neighborhood Cognition Consist Learning Agent Communication Message Pruning

本文链接：https://blog.csdn.net/mmc2015/article/details/103101883

版权

本文介绍了两篇AAAI2020的文章，第一篇提出NCC-MARL框架，通过邻域认知一致性解决大规模多智能体合作问题，利用VAE和GNN实现；第二篇提出Gated-ACML，采用门控机制动态修剪通信消息，以适应有限带宽下的多智能体协作，侧重于Q-value的优化策略。

摘要由CSDN通过智能技术生成

第一篇：NCC-MARL: Neighborhood Cognition Consistent Multi-Agent Reinforcement Learning.

NCC-MARL is a general RL framework to handle large-scale multi-agent cooperative problems.
We notice that agents maintain consistent cognitions about their environments are crucial for achieving effective system-level cooperation. In contrast, it is hard to imagine that the agents without consensuses on their situated environments can cooperate well.
NCC-MARL decomposes all agents into much smaller neighborhoods. Furthermore, we assume that each neighborhood has a true hidden cognitive variable, then all neighboring agents learn to align their learned neighborhood-specific cognitive representations with this true hidden cognitive variable by variational inference. As a result, all neighboring agents will eventually form consistent neighborhood cognitions, and thus achieve effective cooperations.
NCC-MARL achieves much better perfor