|
|
9bc1a8ba9f
|
save and restore number of trained episodes
|
2018-03-10 00:22:20 +01:00 |
|
|
|
fc88c64452
|
train and eval now outputs proper number of training episodes to log
|
2018-03-09 21:05:38 +01:00 |
|
|
|
b49946e42c
|
Added player type and possibility of playing against network as player
|
2018-03-09 14:19:31 +01:00 |
|
|
|
30183448ec
|
woooow
|
2018-03-08 16:27:16 +01:00 |
|
|
|
a33826219d
|
I think we can play against a random bot now
|
2018-03-08 13:32:40 +01:00 |
|
|
|
bae1e73692
|
Now only using one bot again. Also changed learning rate to 0.1
|
2018-03-07 14:44:17 +01:00 |
|
|
|
11d25603cf
|
Might be able to learn now (?)
|
2018-03-06 16:23:08 +01:00 |
|
|
|
d2b1f5d523
|
flips
|
2018-03-06 13:04:47 +01:00 |
|
|
|
22870b90d3
|
things are better now
|
2018-03-06 11:06:38 +01:00 |
|
|
|
d3fe3c918c
|
Potentially functioning network
|
2018-03-04 17:35:36 +01:00 |
|
|
|
275689c002
|
Bot reimplemented with new representation.
Fixed bug where black could not bear off.
More tests written.
|
2018-02-22 14:01:28 +01:00 |
|
|
|
bd87ed86d0
|
does not work, but is improved
|
2018-02-13 14:38:49 +01:00 |
|
|
|
fffc8cda85
|
improvements
|
2018-02-07 16:27:03 +01:00 |
|
|
|
d7b1e1e5dd
|
renamed hooman.py -> human.py
|
2018-02-07 16:08:59 +01:00 |
|
|
|
c2118d0549
|
Added network
|
2018-02-07 15:31:05 +01:00 |
|
|
|
3c0625ef47
|
Changed look of board, now using -1 and 1 as players, cleaner, easier and faster
|
2018-02-06 23:29:51 +01:00 |
|
|
|
ea9b8d3feb
|
Now actually has a bot playing, although randomly, it still works
|
2018-02-05 23:50:31 +01:00 |
|
|
|
34264fe8c4
|
initial commit
|
2018-02-05 22:31:34 +01:00 |
|
