issues
search
mokemokechicken
/
reversi-alpha-zero
Reversi reinforcement learning by AlphaGo Zero methods.
MIT License
677
stars
170
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Replacing CNN with decoder-only Transformer for possible acceleration?
#50
AranKomat
opened
6 years ago
3
AlphaZero Approach
#49
JackThomson2
closed
6 years ago
2
a question about reloading model
#48
gooooloo
closed
6 years ago
2
Child seeds being identical to the parent seed may nullify the effect of multi-processing/threading
#47
AranKomat
closed
6 years ago
3
Feature/share sim of another side
#46
mokemokechicken
closed
6 years ago
0
try to implement shared_var
#45
mokemokechicken
closed
6 years ago
0
write self play logs as tensorboard format
#44
mokemokechicken
closed
6 years ago
0
how much does share_mtcs_info_in_self_play contribute in strength?
#43
gooooloo
closed
6 years ago
7
Unofficial AlphaGoZero implementation from Googlers
#42
gooooloo
closed
6 years ago
15
Feature/multiprocess selfplay
#41
mokemokechicken
closed
6 years ago
0
Performance Reports
#40
mokemokechicken
opened
6 years ago
23
automatically ntest
#39
gooooloo
closed
6 years ago
2
It may forget pertinent information about positions that it no longer visits.
#38
apollo-time
opened
6 years ago
21
The history dates of Challenge 3/4 are wrong.
#37
sbbdms
closed
6 years ago
1
Feature/share mcts info in self play
#36
mokemokechicken
closed
6 years ago
0
The sign of virtual loss is reversed
#35
mokemokechicken
closed
6 years ago
0
impl hint protocol
#34
mokemokechicken
closed
6 years ago
0
Feature/support nboard protocol
#33
mokemokechicken
closed
6 years ago
0
What's different between Challenge 2 & 3?
#32
gooooloo
closed
6 years ago
2
Fix GPU ResourceExhaustedError after many times of Keras model.load() during self-play
#31
HaoshengZou
closed
6 years ago
3
GPU ResourceExhaustedError after many times of Keras model.load() during self-play
#30
HaoshengZou
closed
6 years ago
1
invalid correct moves
#29
apollo-time
closed
6 years ago
2
add simple tensorboard callback #27
#28
mokemokechicken
closed
6 years ago
0
About the optimizer?
#27
wjllance
opened
6 years ago
5
Baseline Comparison?
#26
mrlooi
opened
6 years ago
39
404 in the new download script
#25
evalon32
closed
6 years ago
1
About the time of self-play
#24
rtz19970824
opened
6 years ago
3
Is it multiple searching at the same time?
#23
apollo-time
opened
6 years ago
24
Policy out softmax with illegal moves
#22
apollo-time
opened
6 years ago
4
Added environment.yml and updated readme.
#21
mationai
closed
6 years ago
2
Update readme.md
#20
mationai
closed
6 years ago
1
Failed running GUI
#19
mationai
closed
6 years ago
5
Drop wxPython?
#18
breezewish
opened
6 years ago
1
About MCTS
#17
apollo-time
opened
6 years ago
8
Random flip and rotation when evaluate
#16
apollo-time
closed
6 years ago
1
What is action_by_value?
#15
apollo-time
closed
6 years ago
1
Feature/refine implementation
#14
mokemokechicken
closed
6 years ago
0
Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
#13
mokemokechicken
opened
6 years ago
7
Create .env file
#12
wonderkid27
opened
7 years ago
1
Another resign condition?
#11
gooooloo
closed
7 years ago
4
ChessAlpha Zero development
#10
Zeta36
opened
7 years ago
6
implement resign
#9
mokemokechicken
closed
7 years ago
0
Implement resign
#8
mokemokechicken
closed
7 years ago
0
Is 0.55 too high for replace_rate given Reversi can have draw result?
#7
gooooloo
closed
7 years ago
3
[FIX] play data is not reloaded correctly
#6
gooooloo
closed
7 years ago
1
fix: Player#moves include only moves in playing games. #4
#5
mokemokechicken
closed
7 years ago
0
Player#moves must not include moves in thinking!!
#4
mokemokechicken
closed
7 years ago
0
winner type is 'Winner' not 'Player'
#3
mokemokechicken
closed
7 years ago
0
L2 weight regularisation in loss?
#2
gooooloo
closed
7 years ago
1
Great job!!
#1
Zeta36
opened
7 years ago
31
Previous
Next