hongshaorou/Tianshou

Fork 0

History

rtz19970824 906ced84a3 self play

2017-12-08 17:05:33 +08:00

code-verify

connect policy-value network with leela for code verification

2017-11-16 20:19:18 +08:00

__init__.py

compute score

2017-12-01 01:37:55 +08:00

.gitignore

connect our own network to mcts

2017-11-12 22:40:58 +08:00

data.py

modify AlphaGo

2017-11-08 08:32:07 +08:00

engine.py

connect gtp and gui

2017-12-07 17:51:58 +08:00

game.py

self play

2017-12-08 17:05:33 +08:00

go.py

connect gtp and gui

2017-12-07 17:51:58 +08:00

gtp_wrapper.py

AlphaGo update

2017-11-26 13:36:52 +08:00

multi_gpu.py

Implement the network of AlphaGo

2017-11-04 22:16:43 +08:00

Network_ori.py

AlphaGo update

2017-11-26 13:36:52 +08:00

network_small.py

self play

2017-12-08 17:05:33 +08:00

Network.py

merge gtp

2017-11-28 17:00:10 +08:00

random_data.py

AlphaGo update

2017-11-26 13:36:52 +08:00

README.md

connect policy-value network with leela for code verification

2017-11-16 20:19:18 +08:00

self-play.py

self play

2017-12-08 17:05:33 +08:00

strategy.py

self play

2017-12-08 17:05:33 +08:00

test.py

self play

2017-12-08 17:05:33 +08:00

unit_test.py

minor fix

2017-12-07 21:09:58 +08:00

utils.py

merge gtp

2017-11-28 17:00:10 +08:00

README.md

Reproduce AlphaGo Zero

Network.py

A reimplemented version of pv network which is presented in the nature paper.

code-verify:

Connecting our own policy-value neural network with leela-zero.

checkpoints:

Weights of the policy-value neural network