Learning on a Budget via Teacher Imitation

2021 IEEE Conference on Games (CoG)(2021)

引用 0|浏览7
暂无评分
摘要
Deep Reinforcement Learning (RL) techniques can benefit greatly from leveraging prior experience, which can be either self-generated or acquired from other entities. Action advising is a framework that provides a flexible way to transfer such knowledge in the form of actions between teacher-student peers. However, due to the realistic concerns, the number of these interactions is limited with a bu...
更多
查看译文
关键词
Conferences,Games,Reinforcement learning,Task analysis
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要