arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.07017cs.AIcs.MAcs.RO
收藏

通过环境塑造减轻负面影响

Mitigating Negative Side Effects via Environment Shaping

College of Information and Computer Sciences, University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校信息与计算机科学学院)

Sandhya Saisubramanian, Shlomo Zilberstein

摘要:

在非结构化环境中运行的代理通常会产生负面影响(NSE),这在设计时很难识别。虽然代理可以学习减轻人类反馈的副作用,但这种反馈通常是昂贵的,并且学习的速率对代理的状态表示很敏感。我们研究人类如何帮助代理,超越提供反馈,并利用他们更广泛的知识范围来减轻NSE的影响。我们制定这个问题作为一个人的代理团队与解耦的目标。智能体优化其分配的任务,在此期间,其动作可能产生NSE。人类通过微小的重新配置动作来塑造环境,以减轻代理的副作用的影响,而不影响代理完成其分配任务的能力。我们提出了一个算法来解决这个问题,并分析其理论性质。通过对人类受试者的实验,我们评估了用户进行轻微环境修改以减轻NSE影响的意愿。我们的方法的实证评估表明,所提出的框架可以成功地减轻NSE,而不影响代理的能力,完成其分配的任务。

英文摘要:

Agents operating in unstructured environments often produce negative side effects (NSE), which are difficult to identify at design time. While the agent can learn to mitigate the side effects from human feedback, such feedback is often expensive and the rate of learning is sensitive to the agent's state representation. We examine how humans can assist an agent, beyond providing feedback, and exploit their broader scope of knowledge to mitigate the impacts of NSE. We formulate this problem as a human-agent team with decoupled objectives. The agent optimizes its assigned task, during which its actions may produce NSE. The human shapes the environment through minor reconfiguration actions so as to mitigate the impacts of the agent's side effects, without affecting the agent's ability to complete its assigned task. We present an algorithm to solve this problem and analyze its theoretical properties. Through experiments with human subjects, we assess the willingness of users to perform minor environment modifications to mitigate the impacts of NSE. Empirical evaluation of our approach shows that the proposed framework can successfully mitigate NSE, without affecting the agent's ability to complete its assigned task.

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。

↑