期刊文献+

基于Agent强化学习的地图迁移学习算法

下载PDF
导出
摘要 强化学习是Agent学习中广泛使用的方法,在智能机器人、经济学、工业制造和博弈等领域得到了广泛的应用,但学习速度慢是强化学习的主要不足。迁移学习可从源任务中获得与目标任务相关的知识,利用这些知识去提高学习效率与效果。本文提出Agent地图迁移算法,实现了Agent在不同状态空间下的经验迁移。实现将Agent在简单环境中的学习经验迁移到复杂环境中,实验中验证了算法可加快Agent路径规划速度。
作者 张炎 刘博文
出处 《电子世界》 2014年第15期189-189,共1页 Electronics World
  • 相关文献

参考文献4

二级参考文献13

  • 1Sutton R S. Learning to predict by the methods of temporal difference[J]. Machine Learning. 1988, (3) : 9--44. 被引量:1
  • 2Watkins J C H, Dayan Peter. Q-learning[J]. Machine Learning.1992, (8) : 279--292. 被引量:1
  • 3Sutton R S. Temporal credit assignment in reinforcement learning[D]. University of Massachusetts,Amherst,MA, 1984. 被引量:1
  • 4Masayuki Yamamura, Takashi Onozuka. Reinforcement learning with knowledge by using a stochastic gradient method on a bayesian network[A], Proceedings of the 1998 IEEE International Conference on Neural Networks[C]. May 4-9 1998. Anchorage, Alaska, USA : 2045-- 2050. 被引量:1
  • 5Carlos H C Ribeiro. Embedding a priori knowledge in reinforcement learning[J]. Journal of Intelligent and Robotic Systems. 1998,21:51--71. 被引量:1
  • 6Chi-Hyon Oh, Tomoharu Nakashima, Hisao Ishibuchi. Initialization of Q-values by fuzzy rules for accelerating Q-learning[A].Proceedings of the 1998 IEEE International Conference on Neural Networks[C]. May 4-9 1998. Anchorage, Alaska, USA: 2051- 2056. 被引量:1
  • 7Dean F Hougen, Maria Gini, James Slagle. Partitioning input space for reinforcement learning for control. Proceedings of the 1997 IEEE International Congress on Neural Networks.June 9--12, 1997. Houston, TX, USA: 755--760. 被引量:1
  • 8Yoshikazu Arai, Teruo Fujii, Hajime Asama, Yasushi Kataoka.Multilayered reinforcement learning for complicated collision avoidance problems[A]. Proceedings of the 1998 IEEE International Conference on Robotics & Automation[C]. May 16--20,1998. Leuven. Belgium: 2186--2191. 被引量:1
  • 9John W Sheppard. Colearning in Differential Games. Machine Learning. 1998, (33) : 201--233. 被引量:1
  • 10Michael L Littman. Markov games as a framework for muhiagent reinforcement learning[A], Proceedings of the 11th International Conference on Machine Learning. 1994, 157--163. 被引量:1

共引文献6

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部