• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>8th International Workshop on Intelligent Agents VIII: Agent Theories, Architectures, and Languages ATAL 2001, Aug 1-3, 2001, Seattle, WA, USA >Revisiting Asimov's First Law: A Response to the Call to Arms
【24h】

Revisiting Asimov's First Law: A Response to the Call to Arms

机译：重温阿西莫夫第一定律：对号召性武器的回应

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The deployment of autonomous agents in real applications promises great benefits, but it also risks potentially great harm to humans who interact with these agents. Indeed, in many applications, agent designers pursue adjustable autonomy (AA) to enable agents to harness human skills when faced with the inevitable difficulties in making autonomous decisions. There are two key shortcomings in current AA research. First, current AA techniques focus on individual agent-human interactions, making assumptions that break down in settings with teams of agents. Second, humans who interact with agents want guarantees of safety, possibly beyond the scope of the agent's initial conception of optimal AA. Our approach to AA integrates Markov Decision Processes (MDPs) that are applicable in team settings, with support for explicit safety constraints on agents' behaviors. We introduce four types of safety constraints that forbid or require certain agent behaviors. The paper then presents a novel algorithm that enforces obedience of such constraints by modifying standard MDP algorithms for generating optimal policies. We prove that the resulting algorithm is correct and present results from a real-world deployment.
机译：在实际应用程序中部署自治代理有望带来巨大的好处，但同时也可能给与这些代理进行交互的人员带来潜在的巨大伤害。确实，在许多应用中，代理设计人员追求可调整的自主权（AA），以使代理在面临做出自主决策的不可避免困难时能够利用人员的技能。当前的机管局研究存在两个主要缺陷。首先，当前的机管局技术侧重于个体代理人与人之间的互动，做出的假设在代理团队的环境中被打破。第二，与代理人互动的人希望获得安全性的保证，这可能超出了代理人最初对最佳AA的构想。我们的机管局方法集成了适用于团队环境的马尔可夫决策过程（MDP），并支持对代理人行为的明确安全约束。我们介绍了四种禁止或要求某些代理行为的安全约束。然后，本文提出了一种新颖的算法，该算法通过修改用于生成最佳策略的标准MDP算法来强制遵守这些约束。我们证明了生成的算法是正确的，并提供了来自实际部署的结果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号