Interactive Explanations: Diagnosis and Repair of Reinforcement Learning Based Agent Behaviors
2021 IEEE Conference on Games (CoG)(2021)
摘要
Reinforcement learning techniques successfully generate convincing agent behaviors, but it is still difficult to tailor the behavior to align with a user's specific preferences. What is missing is a communication method for the system to explain the behavior and for the user to repair it. In this paper, we present a novel interaction method that uses interactive explanations using templates of nat...
更多查看译文
关键词
Conferences,Natural languages,Cloning,Games,Reinforcement learning,Communication channels,Maintenance engineering
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