issues
search
junxiaosong
/
AlphaZero_Gomoku
An implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row)
MIT License
3.34k
stars
971
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
大棋盘的一点问题
#40
gmftbyGMFTBY
opened
6 years ago
7
关于self.data_buffer.extend(play_data)
#39
huyp182
closed
6 years ago
2
关于entropy
#38
TZWwww
opened
6 years ago
3
如何把weight的参数保存为txt文件呢？
#37
biasbb
closed
6 years ago
0
如何保存权重weight文件呢
#36
biasbb
opened
6 years ago
4
train的时候这个data_buffer满了以后以前的数据会自动出去让新的进来吗？
#35
huyp182
closed
6 years ago
5
TF NCHW->NHWC
#34
Observerspy
closed
6 years ago
5
关于GPU利用率的问题
#33
huyp182
closed
6 years ago
8
关于训练后的模型转换
#32
frendguo
opened
6 years ago
1
关于对gpu的需求的疑问
#31
huyp182
opened
6 years ago
1
Why -leaf_value at mcts_alphaZero.py line 66?
#30
wmpeng
closed
6 years ago
2
minor fix in tensorflow support
#29
dshnightmare
closed
6 years ago
0
Tensorflow版本的疑问
#28
dshnightmare
opened
6 years ago
14
wondering about the input of model
#27
GeneZC
opened
6 years ago
1
采用人工对战数据加快收敛 可行性分析
#26
apple1987
opened
6 years ago
6
Why is the negative leaf_value for update_recursive function?
#25
KelleyYin
opened
6 years ago
7
MCTS最终得出的行为%pi的问题
#24
xiaoyangzai
opened
6 years ago
5
gif是用什么画出来的呢
#23
initial-h
closed
6 years ago
3
Neural Network Architecture
#22
DailinH
opened
6 years ago
2
如果是可以走棋的游戏 action网络应该怎样设计？
#21
fupip
closed
6 years ago
2
MCTS_Pure是啥啊？
#20
jianq1994
closed
6 years ago
1
Better performance.
#19
cxgreat2014
closed
6 years ago
0
Keras support
#18
MingxuZhang
closed
6 years ago
4
softmax 中减去prob最大值的目的
#17
xueyingliu
closed
6 years ago
2
棋盘增大后是不是需要增加CNN的层数呢？
#16
huyp182
opened
6 years ago
11
请问你的电脑配置是什么呢，想参考一下
#15
LeungH
opened
6 years ago
8
遇到好像是陷入了local minimum的问题
#14
GeneZC
closed
6 years ago
17
如果想在15*15的棋盘上获得较好的结果，不知道pure_mcts和simulation的play out应大概设为多少呢？
#13
huyp182
closed
6 years ago
13
Can you pleaase provide a python3 version, thank you!
#12
CaptainEven
closed
6 years ago
1
小白的猜想，请多多指教。
#11
1715509415
closed
6 years ago
3
c_puct 这个参数是什么意思？
#10
1715509415
closed
6 years ago
3
Support tensorflow
#9
Kelvin-Zhong
closed
6 years ago
2
为什么6*6*4train了一天还是0win10loss呢，而且还是乱下棋。。。是不是要修改什么？
#8
huyp182
closed
6 years ago
10
想请问一下楼主有试过在evaluate的时候用最新训练的model和上一次得到的model做对比吗？
#7
Kelvin-Zhong
closed
6 years ago
1
support pytorch GPU training
#6
BIGBALLON
closed
6 years ago
0
state_dict in pytorch isn't compatible with params with theano
#5
GeneZC
closed
6 years ago
5
update Requirements installation
#4
BIGBALLON
closed
6 years ago
0
No module named cPickle
#3
wlonging
closed
6 years ago
2
Support gomocup protocol
#2
tianshuo
closed
6 years ago
2
No module named 'numpy.core.multiarray\r'
#1
initial-h
closed
6 years ago
6
Previous