arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.12938cs.HC
收藏

交互式诊断:基于强化学习的Agent行为诊断与修复

Interactive Explanations: Diagnosis and Repair of Reinforcement Learning Based Agent Behaviors

Christian Arzate Cruz, Takeo Igarashi

摘要:

强化学习技术成功地生成了令人信服的代理行为,但仍然很难定制行为以符合用户的特定偏好。在本文中,我们提出了一种新的交互方法,使用交互式解释,使用模板的自然语言作为一种通信方法。这种交互方法的主要优点是,它使用户和代理之间的双向通信通道;机器人可以解释其思维过程的用户,用户可以使用相同的交互式解释传达他们的行为偏好的机器人。通过这种方式,机器人的思维过程是透明的,用户可以向机器人提供纠正,包括建议采取的行动,要实现的目标以及这些决定背后的原因。我们在一个名为\textit{Super Mario Bros.}的视频游戏克隆中测试了我们提出的方法,结果表明我们的交互式解释方法在诊断和修复机器人行为方面是有效的。

英文摘要:

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 natural language as a communication method. The main advantage of this interaction method is that it enables a two-way communication channel between users and the agent; the bot can explain its thinking procedure to the users, and the users can communicate their behavior preferences to the bot using the same interactive explanations. In this manner, the thinking procedure of the bot is transparent, and users can provide corrections to the bot that include a suggested action to take, a goal to achieve, and the reasons behind these decisions. We tested our proposed method in a clone of the video game named \textit{Super Mario Bros.}, and the results demonstrate that our interactive explanation approach is effective at diagnosing and repairing bot behaviors.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑