摘要: 完整代码:https://github.com/zle1992/Reinforcement_Learning_Game 论文《Continuous control with deep reinforcement learning》https://arxiv.org/pdf/1509.02971.pd 阅读全文
posted @ 2019-01-09 22:41 乐乐章 阅读(4375) 评论(0) 推荐(0) 编辑
摘要: 完整代码:https://github.com/zle1992/Reinforcement_Learning_Game Policy Gradient 可以直接预测出动作,也可以预测连续动作,但是无法单步更新。 QLearning 先预测出Q值,根据Q值选动作,无法预测连续动作、或者动作种类多的情况 阅读全文
posted @ 2019-01-09 12:12 乐乐章 阅读(2053) 评论(0) 推荐(0) 编辑
摘要: Given a 2D board and a word, find if the word exists in the grid. The word can be constructed from letters of sequentially adjacent cell, where "adjac 阅读全文
posted @ 2019-01-09 10:18 乐乐章 阅读(145) 评论(0) 推荐(0) 编辑