hongshaorou/Tianshou

Fork 0

History

Tongzheng Ren 891c5b1e47 Merge branch 'master' of https://github.com/sproblvem/tianshou

2018-01-08 21:21:08 +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

delete unused code

2017-12-26 19:29:35 +08:00

data_statistic.py

count the winning rate for each player

2017-12-23 22:05:34 +08:00

engine.py

delete unused code

2017-12-26 19:29:35 +08:00

game.py

merge

2017-12-29 03:31:57 +08:00

go.py

use hash table for check_global_isomorphous

2017-12-29 03:30:09 +08:00

model.py

debug: we should estimate our own win rate

2018-01-08 16:19:59 +08:00

multi_gpu.py

play

2017-12-09 21:41:11 +08:00

play.py

modify play.py for avoiding potential bug

2018-01-08 21:19:17 +08:00

player.py

debug for reversi

2017-12-28 15:55:07 +08:00

README.md

merge class strategy with class game. Next, merge Go with GoEnv

2017-12-15 22:19:44 +08:00

reversi.py

Merge branch 'master' of https://github.com/sproblvem/tianshou

2017-12-31 15:56:19 +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

README.md

Reproduce AlphaGo Zero

Network.py

code-verify:

checkpoints:

File Specification