datawhalechina/easy-rl issues and pull requests

#166 - RuntimeError: in a2c.py An attempt has been made to start a new process before the current process has finished its bootstrapping phase. This probably means that you are not using fork to start your child processes and you have forgotten to use the proper idiom in the main module

Issue - State: open - Opened by chensisi0730 9 days ago

#165 - There are one suggestion for a word

Issue - State: closed - Opened by shi-yang999 about 1 month ago - 2 comments
Labels: typo

#164 - 运行Q-learning探索策略研究.ipynb时报错： AttributeError: 'numpy.random._generator.Generator' object has no attribute 'rand'

Issue - State: open - Opened by jay-bo 3 months ago

#163 - 第三章第四节书中60页价值函数是单调的证明过程是不是有问题？

Issue - State: closed - Opened by lixinliu1995 4 months ago - 2 comments

#162 - udpate chap4

Pull Request - State: closed - Opened by goodmorning-hwt 4 months ago

#161 - 关于全书结构的建议

Issue - State: closed - Opened by chenslcool 4 months ago - 1 comment

#160 - Typo 汇总

Issue - State: open - Opened by qiwang067 5 months ago - 3 comments
Labels: typo

#159 - Update chapter1.md

Pull Request - State: closed - Opened by GorgeousWang 6 months ago

#158 - /chapter14/chapter14

Issue - State: open - Opened by qiwang067 6 months ago

#157 - /chapter14/chapter14

Issue - State: closed - Opened by qiwang067 6 months ago

#156 - /chapter14/chapter14

Issue - State: closed - Opened by qiwang067 6 months ago

#155 - 《9.3 优势演员-评论员算法》的公式（9.3）错误

Issue - State: closed - Opened by Sjtu-hyg 6 months ago - 3 comments

#154 - TypeError: init() got an unexpected keyword argument 'new_step_api'

Issue - State: closed - Opened by morning-hao 6 months ago - 3 comments

#153 - notebooks/Q-learning/QLearning.ipynb的绘图代码存在一个小瑕疵

Issue - State: closed - Opened by 976213951 6 months ago - 1 comment

#152 - 关于条件全期望公式的推导的问题

Issue - State: closed - Opened by SacuraA 8 months ago - 1 comment

#151 - 纸质版是怎么做的？

Issue - State: closed - Opened by powergiant 9 months ago - 1 comment

#150 - dqn算法问题

Issue - State: closed - Opened by ecsfu 10 months ago

#149 - 连续动作空间的PPO算法

Issue - State: closed - Opened by YZH-WDNMD 11 months ago - 2 comments

#148 - Update chapter10.md 修改黄金状态（gold state）为目标状态（goal state）

Pull Request - State: closed - Opened by taojunhui about 1 year ago

#147 - PPO算法的实现, 为啥要给概率取对数?

Issue - State: closed - Opened by chzhan about 1 year ago - 2 comments

#146 - 关于书中DDPG算法的疑问

Issue - State: open - Opened by yxz777 about 1 year ago - 1 comment

#145 - [fix] 括号不匹配

Pull Request - State: closed - Opened by ssccinng about 1 year ago

#144 - DDPG算法实现出现问题

Issue - State: closed - Opened by yxz777 about 1 year ago

#143 - 图6.8左下角标识应该是“动作价值(Q)”?

Issue - State: closed - Opened by xuleimath about 1 year ago - 1 comment

#142 - 我在运行DQN代码时，初始的state总会多一个值。

Issue - State: closed - Opened by yxz777 about 1 year ago

#141 - Update chapter1.md

Pull Request - State: closed - Opened by gorgeousdays about 1 year ago

#140 - DuelingDQN.ipynb中可能存在的两个BUG~

Issue - State: open - Opened by libermeng over 1 year ago - 2 comments

#139 - 错别字

Issue - State: closed - Opened by ConnorSiXiong over 1 year ago - 2 comments

#138 - value_iteration 算法不收敛？

Issue - State: open - Opened by chensisi0730 over 1 year ago - 1 comment

#137 - 最新的版本，可以出PDF吗

Issue - State: closed - Opened by chensisi0730 over 1 year ago - 2 comments

#136 - 小勘误

Pull Request - State: closed - Opened by sti1l-0 over 1 year ago - 1 comment

#135 - 4.3 REINFORCE：蒙特卡洛策略梯度

Issue - State: closed - Opened by sungaok over 1 year ago - 1 comment

#134 - SAC代码问题

Issue - State: closed - Opened by QUIlToT over 1 year ago - 2 comments

#133 - 添加参考文献

Issue - State: closed - Opened by RudyGuo over 1 year ago - 1 comment

#132 - 内容勘误？

Issue - State: closed - Opened by QUIlToT over 1 year ago - 3 comments

#131 - Update chapter12.md

Pull Request - State: closed - Opened by Ynjxsjmh over 1 year ago

#130 - 第五章勘误

Issue - State: closed - Opened by notomatoes over 1 year ago - 1 comment

#129 - 随书代码在哪

Issue - State: closed - Opened by GoWithWind2015 over 1 year ago - 6 comments

#128 - Edit problem in Chapter3

Issue - State: closed - Opened by mvllwong almost 2 years ago - 1 comment

#127 - 第四章图4.10标注是不是有误？

Issue - State: closed - Opened by njwm almost 2 years ago - 1 comment

#126 - 1.7.1 Gym示例返回值增多了

Issue - State: closed - Opened by neverevergiveup almost 2 years ago - 3 comments

#125 - the version of numpy

Issue - State: closed - Opened by HanggeAi almost 2 years ago

#124 - 怎么在Linux服务器上运行demo程序？

Issue - State: open - Opened by bjzhb666 almost 2 years ago - 2 comments

#123 - DoubleDQN和DQN的update函数代码好像是一样的

Issue - State: closed - Opened by FinnJob almost 2 years ago - 1 comment

#122 - Spelling mistake

Issue - State: open - Opened by d3ac almost 2 years ago - 1 comment

#121 - DoubleDQN的upadate()中的reward_batch少了.unsqueeze(1)

Issue - State: closed - Opened by beerjtu almost 2 years ago - 1 comment

#120 - MonteCarlo code error

Issue - State: open - Opened by beifeng1937 almost 2 years ago - 1 comment

#119 - Create LICENSE

Pull Request - State: closed - Opened by johnjim0816 almost 2 years ago

#118 - 更正图例指示错误

Pull Request - State: closed - Opened by olianate about 2 years ago

#117 - distinguish Qnet and set detach() on TD target

Pull Request - State: closed - Opened by tlt18 about 2 years ago - 1 comment

#116 - DQN代码错误

Issue - State: closed - Opened by Solitario119 about 2 years ago - 1 comment

#115 - conda的环境需要换成python==3.8了

Issue - State: closed - Opened by ExileSaber about 2 years ago - 1 comment

#114 - PPO advantage calculation

Issue - State: closed - Opened by XinXU-USTC about 2 years ago - 1 comment

#113 - “3.3.1 蒙特卡洛策略评估”中经验均值问题

Issue - State: closed - Opened by paulyzhangSmartNews over 2 years ago - 3 comments

#112 - common文件夹里是不是少个py文件呀

Issue - State: closed - Opened by zl-yang over 2 years ago - 2 comments

#111 - Q-learning 出错

Issue - State: closed - Opened by ZHUGUODONG1 over 2 years ago - 1 comment

#110 - 书写错误

Issue - State: closed - Opened by tools-only over 2 years ago - 1 comment

#109 - TD3 目标策略平滑化的工作原理和原始论文描述不一致

Issue - State: closed - Opened by mabaoer over 2 years ago - 1 comment

#108 - 请问以后会增加MARL算法吗？

Issue - State: closed - Opened by pmy0721 over 2 years ago - 1 comment

#107 - Update chapter1.md

Pull Request - State: closed - Opened by zh4men9 over 2 years ago

#106 - PPO算法状态问题

Issue - State: closed - Opened by hxqup over 2 years ago - 1 comment

#105 - 能否提供代码中主要库的版本

Issue - State: closed - Opened by LeonardWan over 2 years ago - 2 comments

#104 - 电子书图片标注问题

Issue - State: closed - Opened by Ashcaesar over 2 years ago - 1 comment

#103 - 内存使用超出预期

Issue - State: open - Opened by zazada over 2 years ago

#102 - Tutorial Notebook broken (Colab)

Issue - State: closed - Opened by parsarahimi over 2 years ago - 1 comment

#101 - 大佬，为啥我总是显示common.utils调用失败啊

Issue - State: closed - Opened by Tongjijiao over 2 years ago - 1 comment

#100 - dqn的代码错误

Issue - State: closed - Opened by chzhan over 2 years ago - 2 comments

#99 - 在线阅读的地址打不开了

Issue - State: closed - Opened by SoloPro-Git over 2 years ago - 3 comments

#98 - DDPG code error

Issue - State: closed - Opened by XianrenYty over 2 years ago - 1 comment

#97 - No common.plot in folder common.

Issue - State: closed - Opened by xdzhang-xdu over 2 years ago - 1 comment

#96 - 电子版94页和102问题请教

Issue - State: closed - Opened by QUIlToT over 2 years ago - 5 comments

#95 - Dueling DQN 实现中的可能错误

Issue - State: closed - Opened by ShuhuaGao over 2 years ago - 1 comment

#94 - 伪代码错误

Issue - State: closed - Opened by QUIlToT over 2 years ago - 5 comments

#93 - 电子版第40页，策略符号是否出错？

Issue - State: closed - Opened by QUIlToT over 2 years ago - 1 comment

#92 - 68页的代码块缩进错误

Issue - State: closed - Opened by xiaoqingsai over 2 years ago - 2 comments

#91 - 离散的SAC代码

Issue - State: open - Opened by 670555467 over 2 years ago

#90 - QLearning算法可能出现的bug

Issue - State: closed - Opened by stellar749 over 2 years ago - 1 comment

#89 - reinforcement拼写错误

Issue - State: closed - Opened by yintianan over 2 years ago - 1 comment

#88 - 33页中第2章图片错误

Issue - State: closed - Opened by yue2388253 over 2 years ago - 1 comment

#87 - Update chapter11.md

Pull Request - State: closed - Opened by BeBraveBeCurious over 2 years ago

#86 - Update chapter11.md

Pull Request - State: closed - Opened by BeBraveBeCurious over 2 years ago

#85 - /errata

Issue - State: open - Opened by qiwang067 almost 3 years ago
Labels: Gitalk, /errata

#84 - DDPG的代码有很多纰漏

Issue - State: closed - Opened by liuchaohu almost 3 years ago - 2 comments

#83 - PolicyGradient中的import错误

Issue - State: closed - Opened by liuchaohu almost 3 years ago - 2 comments

#82 - bug ?

Issue - State: closed - Opened by jiang-wenbin almost 3 years ago - 1 comment

#81 - PPO算法训练和验证以及测试过程中action_select疑问

Issue - State: closed - Opened by HUSTHY almost 3 years ago - 2 comments

#80 - total_loss = actor_loss + 0.5*critic_loss? PPO中actor与critic网络更新为什么都使用total_loss

Issue - State: open - Opened by CeibaSheep almost 3 years ago - 3 comments

#79 - Update train.py

Pull Request - State: closed - Opened by Magicianlial almost 3 years ago - 1 comment

#78 - Update task0.py

Pull Request - State: closed - Opened by Magicianlial almost 3 years ago - 1 comment

#77 - 请问为什么在这agent中的update计算discount reward时要对reward为0情况进行特别考虑？

Issue - State: closed - Opened by wansiwei0521 almost 3 years ago - 1 comment

#76 - 用Atari的pong游戏代替CartPole策略网络会发生错误

Issue - State: open - Opened by wing-on almost 3 years ago - 1 comment

#75 - plot_rewards（）函数错误

Issue - State: closed - Opened by daihuiao almost 3 years ago - 2 comments

#74 - 这个有cnn版本的吗，都是线性模型

Issue - State: open - Opened by aicools about 3 years ago - 1 comment

#73 - PPO的Critic输入加入Action

Issue - State: open - Opened by Hanbinbinbin about 3 years ago - 1 comment

#72 - 运行程序会有找不到字体包的错误

Issue - State: closed - Opened by djunmaster about 3 years ago - 1 comment

#71 - DQN代码中有bug

Issue - State: closed - Opened by PungTeng about 3 years ago - 3 comments

#70 - Qlearning error

Issue - State: closed - Opened by HRXWEB about 3 years ago - 3 comments

#69 - About SAC

Issue - State: closed - Opened by Bruce-wind over 3 years ago - 3 comments

#68 - add PPO-continuous code

Issue - State: closed - Opened by heyfavour over 3 years ago - 2 comments

#67 - pdf文件太大，建议压缩。此外建议添加国内的pdf下载方式。

Issue - State: closed - Opened by finlay-liu over 3 years ago - 1 comment

GitHub / datawhalechina/easy-rl issues and pull requests