arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.02818cs.HC
收藏

为什么?为什么?为什么不呢?什么时候?强化学习中Agent行为的可视化描述

Why? Why not? When? Visual Explanations of Agent Behavior in Reinforcement Learning

Aditi Mishra, Utkarsh Soni, Jinbin Huang, Chris Bryan

摘要:

强化学习(RL)被用于许多领域,包括自动驾驶、机器人、股票交易和视频游戏。不幸的是,RL代理的黑箱性质,加上法律和道德方面的考虑,使得人类(包括那些不是RL专家的人)理解RL代理所采取的行动背后的推理变得越来越重要,特别是在安全关键领域。为了帮助解决这一挑战,我们引入了PolicyExplainer,这是一个可视化的分析界面,可以让用户直接查询自主智能体。PolicyExplainer可视化代理的状态,策略和预期的未来奖励,并支持询问和回答问题,例如:为什么采取此操作?为什么不采取另一种行动?何时采取这一行动?PolicyExplainer是基于RL研究人员的领域分析而设计的,并通过对三个领域的定性和定量评估进行评估:出租车导航,堆栈机器人领域和HIV患者的药物推荐。我们发现,PolicyExplamer比最先进的基于文本的解释方法更能促进对代理决策的信任和理解。与领域从业者的访谈提供了进一步验证PolicyExplainer应用于安全关键域。我们的研究结果有助于展示如何利用基于可视化的方法来解码自主RL代理的行为,特别是对于RL非专家。

英文摘要:

Reinforcement learning (RL) is used in many domains, including autonomous driving, robotics, stock trading, and video games. Unfortunately, the black box nature of RL agents, combined with legal and ethical considerations, makes it increasingly important that humans (including those are who not experts in RL) understand the reasoning behind the actions taken by an RL agent, particularly in safety-critical domains. To help address this challenge, we introduce PolicyExplainer, a visual analytics interface which lets the user directly query an autonomous agent. PolicyExplainer visualizes the states, policy, and expected future rewards for an agent, and supports asking and answering questions such as: Why take this action? Why not take this other action? When is this action taken? PolicyExplainer is designed based upon a domain analysis with RL researchers, and is evaluated via qualitative and quantitative assessments on a trio of domains: taxi navigation, a stack bot domain, and drug recommendation for HIV patients. We find that PolicyExplainer promotes trust and understanding of agent decisions better than a state-of-the-art text-based explanation approach. Interviews with domain practitioners provide further validation for PolicyExplainer as applied to safety-critical domains. Our results help demonstrate how visualization-based approaches can be leveraged to decode the behavior of autonomous RL agents, particularly for RL non-experts.

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。

↑