Johannes Heinrich 个人学术档案 - 学术资源搜索

引用次数

	总计	2019 年至今
引用	906	752
h 指数	5	5
i10 指数	5	4

0

200

100

50

150

20152016201720182019202020212022202320247 22 37 65 111 106 125 160 187 63

Johannes Heinrich

Johannes Heinrich

University College London

在 cs.ucl.ac.uk 的电子邮件经过验证

Sequential Decision Making Reinforcement Learning Game Theory


标题按引用次数排序按年份排序按标题排序	引用次数引用次数	年份
Deep reinforcement learning from self-play in imperfect-information games J Heinrich, D Silver arXiv preprint arXiv:1603.01121, 2016	466	2016
Fictitious Self-Play in Extensive-Form Games J Heinrich, M Lanctot, D Silver Proceedings of the 32nd International Conference on Machine Learning, 2015	373	2015
Smooth uct search in computer poker J Heinrich, D Silver Twenty-Fourth International Joint Conference on Artificial Intelligence, 2015	36	2015
Self-play Monte-Carlo tree search in computer poker J Heinrich, D Silver Workshops at the Twenty-Eighth AAAI Conference on Artificial Intelligence, 2014	21	2014
Reinforcement learning from self-play in imperfect-information games J Heinrich UCL (University College London), 2017	10	2017

系统目前无法执行此操作，请稍后再试。

文章 1–5

共建清朗的网络空间,如遇有害信息,请举报。
本站数据皆整合自互联网公开资源索引,方便科研学术方面查询,并不存储相关数据资源;如对此有异议,请联系我们解决.
© 2023 学术资源搜索 @联系我们 | 申请短期会员 | 数据源提交