|
|
f43108c239
|
Training using slightly revamped version of our own board rep. Not sure if works yet.
|
2018-03-27 04:06:08 +02:00 |
|
|
|
006f791727
|
Functioning network using board representation shamelessly ripped from Tesauro
|
2018-03-27 02:26:15 +02:00 |
|
|
|
98c9af72e7
|
rework network
|
2018-03-22 15:30:47 +01:00 |
|
|
|
b7e6dd10af
|
move evaluation code into network.py
|
2018-03-20 13:17:38 +01:00 |
|
|
|
99783ee4f8
|
clean up and move things to network.py
|
2018-03-20 13:03:21 +01:00 |
|
|
|
2fc7a2a09c
|
fixed dumb bugs; still messy
|
2018-03-14 20:42:09 +01:00 |
|
|
|
55898d0e66
|
renaming parameters
|
2018-03-12 00:11:55 +01:00 |
|
|
|
9bc1a8ba9f
|
save and restore number of trained episodes
|
2018-03-10 00:22:20 +01:00 |
|
|
|
150036a6cb
|
plot-plot
|
2018-03-08 17:13:25 +01:00 |
|
|
|
30183448ec
|
woooow
|
2018-03-08 16:27:16 +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 |
|
|
|
e7fe827ceb
|
Merge branch 'master' of gitfub.space:Pownie/backgammon
|
2018-03-06 12:22:45 +01:00 |
|
|
|
c9e4446a52
|
Custom activation (2*tanh(x)) function implemented with tensorflow primitives.
|
2018-03-06 12:19:04 +01:00 |
|
|
|
00033a7aca
|
re-enable Tensorflow logging
|
2018-03-06 12:04:56 +01:00 |
|
|
|
5845edf084
|
works now
|
2018-03-06 11:53:42 +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 |
|
|
|
c2118d0549
|
Added network
|
2018-02-07 15:31:05 +01:00 |
|
