• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Intelligent Agent Technology, IEEE/WIC/ACM International Conference on >Self-organizing cognitive agents and reinforcement learning in multi-agent environment
【24h】

Self-organizing cognitive agents and reinforcement learning in multi-agent environment

机译：自组织认知智能体和多智能体环境中的强化学习

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This paper presents a self-organizing cognitive architecture, known as TD-FALCON, that learns to function through its interaction with the environment. TD-FALCON learns the value functions of the state-action space estimated through a temporal difference (TD) method. The learned value functions are then used to determine the optimal actions based on an action selection policy. We present a specific instance of TD-FALCON based on an e-greedy action policy and a Q-learning value estimation formula. Experiments based on a minefield navigation task and a minefield pursuit task show that TD-FALCON systems are able to adapt and function well in a multi-agent environment without an explicit mechanism for collaboration.
机译：本文提出了一种自组织的认知架构，称为TD-FALCON，该架构通过与环境的相互作用来学习其功能。 TD-FALCON学习通过时间差（TD）方法估计的状态-作用空间的值函数。然后，将学习值函数用于基于操作选择策略来确定最佳操作。我们基于电子贪婪行为策略和Q学习价值估计公式，给出了TD-FALCON的特定实例。基于雷场导航任务和雷场追踪任务的实验表明，TD-FALCON系统能够在多主体环境中适应并正常运行，而无需明确的协作机制。

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