Yizhao JinNote of Feudal Networks for Hierarchical Reinforcement LearningAbstract This paper is mainly on the improvement and application of feudal reinforcement learning, First talk about the form of federal…3 min read·Mar 7, 2021----
Yizhao JinAcademic conferences in the field of artificial intelligence1. AAAI Conference on Artificial Intelligence(AAAI)2 min read·Feb 25, 2021----
Yizhao JinResearch plan of MARL communicationSome multi-agent reinforcement learning methods explicitly assume that there is information interaction between agents, and learn how to…3 min read·Feb 25, 2021----
Yizhao JinResearch of MARL communication (note)This article is the first to introduce communication learning in deep multi-agent reinforcement learning, and the reinforcement learning…5 min read·Feb 25, 2021----