issues
search
datawhalechina
/
easy-rl
强化学习中文教程(蘑菇书🍄),在线阅读地址:https://datawhalechina.github.io/easy-rl/
Other
9.04k
stars
1.81k
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
PPO advantage calculation
#114
XinXU-USTC
closed
1 year ago
1
“3.3.1 蒙特卡洛策略评估”中经验均值问题
#113
paulyzhangSmartNews
closed
2 years ago
3
common文件夹里是不是少个py文件呀
#112
zl-yang
closed
1 year ago
2
Q-learning 出错
#111
ZHUGUODONG1
closed
1 year ago
1
书写错误
#110
tools-only
closed
2 years ago
1
TD3 目标策略平滑化的工作原理 和 原始论文描述不一致
#109
mabaoer
closed
2 years ago
1
请问以后会增加MARL算法吗?
#108
pmy0721
closed
1 year ago
1
Update chapter1.md
#107
zh4men9
closed
2 years ago
0
PPO算法状态问题
#106
hxqup
closed
2 years ago
1
能否提供代码中主要库的版本
#105
LeonardWan
closed
1 year ago
2
电子书图片标注问题
#104
Ashcaesar
closed
2 years ago
1
内存使用超出预期
#103
zazada
opened
2 years ago
0
Tutorial Notebook broken (Colab)
#102
parsarahimi
closed
1 year ago
1
大佬,为啥我总是显示common.utils调用失败啊
#101
Tongjijiao
closed
2 years ago
1
dqn的代码错误
#100
chzhan
closed
1 year ago
2
在线阅读的地址打不开了
#99
SoloPro-Git
closed
2 years ago
3
DDPG code error
#98
XianrenYty
closed
1 year ago
1
No common.plot in folder common.
#97
xdzhang-xdu
closed
2 years ago
1
电子版94页和102问题请教
#96
zichunxx
closed
2 years ago
5
Dueling DQN 实现中的可能错误
#95
ShuhuaGao
closed
1 year ago
1
伪代码错误
#94
zichunxx
closed
1 year ago
5
电子版第40页,策略符号是否出错?
#93
zichunxx
closed
2 years ago
1
68页的代码块缩进错误
#92
xiaoqingsai
closed
2 years ago
2
离散的SAC代码
#91
670555467
opened
2 years ago
0
QLearning算法可能出现的bug
#90
stellar749
closed
1 year ago
1
reinforcement拼写错误
#89
yintianan
closed
2 years ago
1
33页中第2章图片错误
#88
yue2388253
closed
2 years ago
1
Update chapter11.md
#87
BeBraveBeCurious
closed
2 years ago
0
Update chapter11.md
#86
BeBraveBeCurious
closed
2 years ago
0
/errata
#85
qiwang067
opened
2 years ago
0
DDPG的代码有很多纰漏
#84
liuchaohu
closed
2 years ago
2
PolicyGradient中的import错误
#83
liuchaohu
closed
2 years ago
2
bug ?
#82
jiang-wenbin
closed
2 years ago
1
PPO算法训练和验证以及测试过程中action_select疑问
#81
HUSTHY
closed
1 year ago
2
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
#80
CeibaSheep
opened
2 years ago
3
Update train.py
#79
Magicianlial
closed
2 years ago
1
Update task0.py
#78
Magicianlial
closed
2 years ago
1
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?
#77
wansiwei0521
closed
2 years ago
1
用Atari的pong游戏代替CartPole策略网络会发生错误
#76
wing-on
opened
2 years ago
1
plot_rewards()函数错误
#75
daihuiao
closed
2 years ago
2
这个有cnn版本的吗,都是线性模型
#74
aicools
opened
2 years ago
1
PPO的Critic输入加入Action
#73
Hanbinbinbin
opened
2 years ago
1
运行程序会有找不到字体包的错误
#72
djunmaster
closed
2 years ago
1
DQN代码中有bug
#71
Hoantrbl
closed
2 years ago
3
Qlearning error
#70
HRXWEB
closed
2 years ago
3
About SAC
#69
peakyet
closed
2 years ago
3
add PPO-continuous code
#68
heyfavour
closed
2 months ago
2
pdf文件太大,建议压缩。此外建议添加国内的pdf下载方式。
#67
finlay-liu
closed
3 years ago
1
表达过于口语化
#66
siliconx
closed
3 years ago
1
question
#65
fiora6
closed
3 years ago
1
Previous
Next