首页> 外军国防科技报告 >AN EVALUATION OF USING DETERMINISTIC HEURISTICS TO ACCELERATE REINFORCEMENT LEARNING
【2h】

AN EVALUATION OF USING DETERMINISTIC HEURISTICS TO ACCELERATE REINFORCEMENT LEARNING

机译:利用决定性启发式加速加强学习的评估

代理获取
代理获取并翻译 | 示例

摘要

Neural networks frequently face long training times based on the corpus of data available to them. Reinforcement learning in particular can take a long time to attain satisfactory performance. Recent efforts to incorporate deterministic logical rules and physical laws into a neural network have met with promising results. From an existing baseline neural network that is designed to learn Pong strictly from pixel representation of the game board, this thesis adds a ball trajectory-based heuristic into the learning process and evaluates its performance. The evaluation initially shows game score improvements, but demonstrates a sharp score degradation after about 25,000 games. Another evaluation shows the heuristic incurs a training time increase of approximately 35%. More work remains for assessing the long-term viability of this approach.

著录项

  • 作者

    Walton, Garret M.;

  • 作者单位
  • 年(卷),期 2019(),
  • 年度 2019
  • 页码
  • 总页数 86
  • 原文格式 PDF
  • 正文语种
  • 中图分类
  • 网站名称 美国海军研究生院图书馆
  • 栏目名称 所有文件
  • 关键词

  • 入库时间 2022-08-19 17:00:19
代理获取

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