profile
viewpoint
Morvan MorvanZhou https://morvanzhou.github.io/ Deep Learning Research & Development in Tencent

MorvanZhou/tutorials 7600

机器学习相关教程

MorvanZhou/Reinforcement-learning-with-tensorflow 4819

Simple Reinforcement learning tutorials

MorvanZhou/PyTorch-Tutorial 4359

Build your neural network easy and fast

MorvanZhou/Tensorflow-Tutorial 3618

Tensorflow tutorial from basic to hard

MorvanZhou/Evolutionary-Algorithm 687

Evolutionary Algorithm using Python

MorvanZhou/easy-scraping-tutorial 430

Simple but useful Python web scraping tutorial code.

MorvanZhou/morvanzhou.github.io 417

莫烦Python Website source code

MorvanZhou/pytorch-A3C 257

Simple A3C implementation with pytorch + multiprocessing

MorvanZhou/Tensorflow-Computer-Vision-Tutorial 196

Tutorials of deep learning for computer vision.

MorvanZhou/train-robot-arm-from-scratch 181

Build environment and train a robot arm from scratch (Reinforcement Learning)

issue closedMorvanZhou/Reinforcement-learning-with-tensorflow

如何限制输出的动作不小于0?

莫凡你好,非常感谢你之前的回复。 我的agent是一个自己定义的简单的模型。 就是一辆车在一条线上跑,但是只能往一个方向跑,所以它的速度只能是不小于0, 请问这个该怎么限制呢? 另外一个问题就是,我把每部的动作输出了一下,发现输出的动作一直在边界上,这是为什么呢?

closed time in 6 days

YingxiaoKong

issue commentMorvanZhou/Reinforcement-learning-with-tensorflow

如何限制输出的动作不小于0?

  1. 将action的取值映射到正值空间上就好了,比如tanh(-1,1)-> (0, 20).
  2. 值在边界上说明agent已经不想在探索了,可以调小学习率,或者是调大探索率。
YingxiaoKong

comment created time in 6 days

issue closedMorvanZhou/tutorials

Is this your website? https://www.echenshe.com/class/tensorflow/

https://www.echenshe.com/class/tensorflow/ Is this your website? It has the same tutorials with yours.

closed time in 8 days

recoversu

issue commentMorvanZhou/tutorials

Is this your website? https://www.echenshe.com/class/tensorflow/

No, this is not mine.

recoversu

comment created time in 8 days

issue closedMorvanZhou/Reinforcement-learning-with-tensorflow

DDPG action 不需要normalize 吗?

我看了你的DDPG的程序,对比了其他人的,觉得非常清晰。但是有一点我不太理解,就是我在论文里面也看到了action和state都需要normalize,但是在你的程序里面并没有看到,请问你是怎么处理呢?

closed time in 11 days

YingxiaoKong

issue commentMorvanZhou/Reinforcement-learning-with-tensorflow

DDPG action 不需要normalize 吗?

这个看情况而定,是可以加上去的。因为测试用的游戏比较简单,state,action不normalize也是可以的。

YingxiaoKong

comment created time in 11 days

push eventMorvanZhou/morvanzhou.github.io

morvanzhou

commit sha 0c7f19fa98edbae78468142758d0d1d375efa48c

fix bug

view details

push time in 11 days

PR closed MorvanZhou/Reinforcement-learning-with-tensorflow

Update Qlearning

把构造天堂和地狱用函数包装了一下,方便自定义地图

+164 -129

1 comment

2 changed files

momogasuki

pr closed time in 11 days

pull request commentMorvanZhou/Reinforcement-learning-with-tensorflow

Update Qlearning

谢谢做出的修改,为了保持和视频的一致性,我还是会保持原代码。

momogasuki

comment created time in 11 days

issue commentMorvanZhou/Reinforcement-learning-with-tensorflow

ddpg算法没有收敛.没有复现视频的结果

Refer to this issue, https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/pull/125

I have changed the code.

zhangbo2008

comment created time in 11 days

pull request commentMorvanZhou/Reinforcement-learning-with-tensorflow

fix a bug in DDPG.py.

I have checked those codes and find this is a bug. Thanks and fixed.

jiangyuzhao

comment created time in 11 days

push eventMorvanZhou/Reinforcement-learning-with-tensorflow

JiangYuzhao

commit sha 2c6c46d59991f9b67e74223b8b1d0b0906d926a6

fix a bug in DDPG.py.

view details

Morvan

commit sha 215f31cc8a9bfa6bd83c96bf583cf2a116f3d8d5

Merge pull request #125 from jiangyuzhao/bugFix fix a bug in DDPG.py.

view details

push time in 11 days

PR merged MorvanZhou/Reinforcement-learning-with-tensorflow

fix a bug in DDPG.py.

if you use a in the program, the gradient will always be None.

+1 -1

8 comments

1 changed file

jiangyuzhao

pr closed time in 11 days

push eventMorvanZhou/morvanzhou.github.io

Morvan Zhou

commit sha 9025143026b2cc1fa46f4e59aac56c5bd1ca9d24

修改广告

view details

push time in 2 months

push eventMorvanZhou/morvanzhou.github.io

Morvan Zhou

commit sha 39cce66068192e1ef46b15525f1c70e6d2d04d46

修改广告

view details

push time in 2 months

push eventMorvanZhou/morvanzhou.github.io

Morvan Zhou

commit sha e932c0ede8fc9cbf98771082f8c3211067e785e7

修改广告

view details

push time in 2 months

push eventMorvanZhou/morvanzhou.github.io

Morvan Zhou

commit sha b7f9c562c4acbbefa11cda17ff914096a049a3fd

修改广告

view details

push time in 2 months

push eventMorvanZhou/morvanzhou.github.io

Morvan Zhou

commit sha 1a76eee526a370aeb2e1927c7f104a3cdcbfeb52

取消 lazy img

view details

push time in 2 months

push eventMorvanZhou/morvanzhou.github.io

Morvan Zhou

commit sha 2c6df03955db697eb177324a04ba82d2332a6348

update

view details

push time in 2 months

push eventMorvanZhou/morvanzhou.github.io

morvanzhou

commit sha fcd57db0e8a59df4119aedd80b1b8a9cf7b2476d

update

view details

push time in 2 months

push eventMorvanZhou/morvanzhou.github.io

morvanzhou

commit sha c302217061f090b1c6473e8307f5a28f3c5af06a

update

view details

push time in 2 months

push eventMorvanZhou/morvanzhou.github.io

morvanzhou

commit sha 43c1971b738ca6490cd0262777ea8931a441beb6

update

view details

push time in 2 months

push eventMorvanZhou/morvanzhou.github.io

morvanzhou

commit sha 81e37c85c577cc28bc46a1d109de12297dfcb817

update

view details

push time in 2 months

push eventMorvanZhou/morvanzhou.github.io

morvanzhou

commit sha 5f0fd367e0f3b02d2ff893238a2a3d6f73259c41

update

view details

push time in 2 months

push eventMorvanZhou/morvanzhou.github.io

morvanzhou

commit sha af464d2809327d7f8f054a8189c3612051abdc5a

update

view details

push time in 2 months

push eventMorvanZhou/go-unit-test-demo

morvanzhou

commit sha 60913abbe0e9950b20b08734d56e79fb0fe40879

path update

view details

push time in 3 months

push eventMorvanZhou/go-unit-test-demo

morvanzhou

commit sha 0d655abbcc27c7e70beba59554486255910f2216

update

view details

push time in 3 months

push eventMorvanZhou/go-unit-test-demo

morvanzhou

commit sha 13090ff97d6b5448656bc8ae04053e9a99aa58a4

update

view details

push time in 3 months

push eventMorvanZhou/go-unit-test-demo

morvanzhou

commit sha 901d14d53403cabc785cea4eada95541f9694a44

gomonkey mock

view details

push time in 3 months

push eventMorvanZhou/go-unit-test-demo

morvanzhou

commit sha 4467c219a25324aa074cad1cbb3ef83806e0219b

gomonkey mock

view details

push time in 3 months

push eventMorvanZhou/go-unit-test-demo

morvanzhou

commit sha f40334ce1d423fd6c82451ee1306e74be2c0ebb5

api test

view details

push time in 3 months

push eventMorvanZhou/go-unit-test-demo

morvanzhou

commit sha 71b61e55358678491df6def929f34baa228cace0

api test

view details

push time in 3 months

push eventMorvanZhou/go-unit-test-demo

morvanzhou

commit sha fedaeba25b85f29a195a083e2e1260b9a1f218c1

update

view details

push time in 3 months

push eventMorvanZhou/go-unit-test-demo

morvanzhou

commit sha 76294a6ffb38e8561e3cfedfac1aeb4538edf3b0

update

view details

push time in 3 months

startedMorvanZhou/go-unit-test-demo

started time in 3 months

create barnchMorvanZhou/go-unit-test-demo

branch : master

created branch time in 3 months

created repositoryMorvanZhou/go-unit-test-demo

some golang unit test demos

created time in 3 months

push eventMorvanZhou/Meta-Learning

morvanzhou

commit sha c716cdea8676c9e18a90d4373503bbc1071a2629

update

view details

push time in 3 months

push eventMorvanZhou/Meta-Learning

morvanzhou

commit sha 9aae02307f046307e65cc9e1bef23ed314b5ae2d

update

view details

push time in 3 months

push eventMorvanZhou/Meta-Learning

morvanzhou

commit sha 51d27ab2ae4e5099816fc4d2b329557758be82ce

update

view details

push time in 3 months

push eventMorvanZhou/Meta-Learning

morvanzhou

commit sha cadfdb722bff0f115df449e28cdc754f14b3bf7e

add license

view details

push time in 3 months

create barnchMorvanZhou/Meta-Learning

branch : master

created branch time in 3 months

created repositoryMorvanZhou/Meta-Learning

created time in 3 months

push eventMorvanZhou/Tensorflow2-Tutorial

morvanzhou

commit sha 2deef764e3cce745f20b9ed4c66740db2f444f97

update

view details

push time in 4 months

push eventMorvanZhou/Tensorflow2-Tutorial

morvanzhou

commit sha b6da6a22118d0fc7c335c0f5a904445b7d2da998

update

view details

morvanzhou

commit sha df38cc9b1a33e37d06318a77139f15010502cf33

remove input shape

view details

push time in 4 months

startedjindongwang/transferlearning-tutorial

started time in 4 months

push eventMorvanZhou/Tensorflow2-Tutorial

morvanzhou

commit sha d2b2b23b0c3f1cd538e3ef4d5b4ff1076a1cf602

update

view details

push time in 4 months

startedjindongwang/maml

started time in 4 months

push eventMorvanZhou/Tensorflow2-Tutorial

morvanzhou

commit sha 4b2d5767fbd8a56bd20b4f82f64af125ff7b47dd

update

view details

push time in 4 months

startedMorvanZhou/Tensorflow2-Tutorial

started time in 4 months

push eventMorvanZhou/Tensorflow2-Tutorial

morvanzhou

commit sha e8bb23ab8a5218a1d7e0c9d785fe7cf9438e6832

update

view details

push time in 4 months

push eventMorvanZhou/Tensorflow2-Tutorial

morvanzhou

commit sha 1eceb269eb9d2911cef700e6f81ad27db14df574

init

view details

morvanzhou

commit sha cd6b43778256b989bc3cedc5dfbd6d182487ba63

Merge branch 'master' of https://github.com/MorvanZhou/Tensorflow2-Tutorial

view details

push time in 4 months

create barnchMorvanZhou/Tensorflow2-Tutorial

branch : master

created branch time in 4 months

created repositoryMorvanZhou/Tensorflow2-Tutorial

Tensorflow 2.0 toy examples

created time in 4 months

startedbndr/pipreqs

started time in 4 months

push eventMorvanZhou/pytorch-A3C

Justin

commit sha af85488ff60d674943518fd742bffce0d6f0d40d

Added matplotlib to requirements

view details

Morvan

commit sha 6ee65a803d9659f5f1ef91a2430f36e334e8f4ae

Merge pull request #11 from Jbwasse2/master Added matplotlib to requirements

view details

push time in 4 months

pull request commentMorvanZhou/pytorch-A3C

Added matplotlib to requirements

Thanks.

Jbwasse2

comment created time in 4 months

more