search

ermongroup / MA-AIRL

Multi-Agent Adversarial Inverse Reinforcement Learning, ICML 2019.
184 stars 28 forks source link

问一个学术上投稿的问题 #1

Closed ZhangNYG closed 5 years ago

ZhangNYG commented 5 years ago

Multi-Agent Generative Adversarial Imitation Learning ICLR 2018 Workshop Multi-Agent Adversarial Inverse Reinforcement Learning, ICML 2019. 这两篇论文 不能算是一稿多投是吧

jiamings commented 5 years ago

这两个文章讨论的不是一个问题，后者是前者的follow up。 后者的算法比前者多了学习agent的reward function，并且两个文章的multi-agent RL的设定也不太一样，前者是从Nash Equilibrium，后者是从一种Quantal response equilibrium出发的。