785ae6a5be
Fixed wrongful appending of current player to board rep
2018-03-28 00:16:50 +02:00
2654006222
fix wrongful mergings
2018-03-27 13:02:36 +02:00
28b82e8228
update dumbeval weights
2018-03-27 12:57:06 +02:00
8822af81e6
move dumbeval code to separate directory
2018-03-27 12:23:15 +02:00
5e5b3981fc
Merge branch 'fuck_git' into 'rework-1'
...
Merge branch 'rework-1' into 'fuck_git'
See merge request Pownie/backgammon!3
2018-03-27 10:19:50 +00:00
d4e699bc49
Merge branch 'rework-1' into 'fuck_git'
...
Rework 1
See merge request Pownie/backgammon!2
2018-03-27 10:16:37 +00:00
c248ca0452
Merge branch 'fuck_git' into 'rework-1'
...
# Conflicts:
# network.py
2018-03-27 10:15:51 +00:00
0eac5434d6
update .gitignore
2018-03-27 11:55:32 +02:00
f43108c239
Training using slightly revamped version of our own board rep. Not sure if works yet.
2018-03-27 04:06:08 +02:00
ab5d2aabb2
Initialized weights completely randomly for dumbeval
2018-03-27 02:41:58 +02:00
006f791727
Functioning network using board representation shamelessly ripped from Tesauro
2018-03-27 02:26:15 +02:00
9b2bbfb4d1
print variances when plotting evaluation variance benchmark
2018-03-26 17:06:12 +02:00
4c43bf19a3
Add evaluation variance benchmark
...
To do a benchmark for `pubeval`, run `python3 main.py --bench-eval-scores
--eval-methods pubeval`
Logs will be placed in directory `bench`
Use `plot_bench(data_path)` in `plot.py` for plotting
2018-03-26 16:45:26 +02:00
1f1e806306
fix errant whitespace
2018-03-26 15:55:48 +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
9b96cf41da
update .gitignore
2018-03-20 13:03:01 +01:00
2fc7a2a09c
fixed dumb bugs; still messy
2018-03-14 20:42:09 +01:00
08481e508a
oops
2018-03-14 14:02:56 +01:00
5caae5b935
spring cleaning 1
2018-03-14 14:02:19 +01:00
fcc373c0d8
update pubeval to take tuples of proper length as input
2018-03-14 12:47:27 +01:00
57367329ec
Merge branch 'master' of gitfub.space:Pownie/backgammon
2018-03-14 11:45:19 +01:00
f009809d39
README for pubeval
2018-03-14 11:44:55 +01:00
b7e7b52e7c
add "race" parameter to pubeval
2018-03-14 11:44:46 +01:00
4b907d30cf
add .gitignore to pubeval/
2018-03-14 11:44:34 +01:00
77645eaf8e
Update README.org
2018-03-14 10:19:17 +00:00
6709a4bb1c
README extended to include new pubeval
2018-03-14 11:12:11 +01:00
d52e4a597c
pubeval is now a C-extension to Python
2018-03-14 11:07:43 +01:00
153776d83e
fix bin/save_model
2018-03-14 11:06:55 +01:00
7b0e60f069
self is difficult to remember
2018-03-13 08:55:54 +01:00
520ca077fd
Fixed min hovedet under armen kode
2018-03-13 00:05:30 +01:00
d275955296
Hovedet under armen udgaven
2018-03-12 22:57:15 +01:00
81f8db35f4
clean up
2018-03-12 15:18:44 +01:00
554e587ffd
somewhat working plots
2018-03-12 00:12:03 +01:00
55898d0e66
renaming parameters
2018-03-12 00:11:55 +01:00
90b97da4ff
pubeval evaluation
2018-03-12 00:11:40 +01:00
ac924f655b
remove pubeval binary and change expected binary location
2018-03-12 00:09:33 +01:00
5e937d68b4
Added a bunch of pubeval stuff
2018-03-11 20:00:24 +01:00
81461d917e
update README
2018-03-11 13:11:27 +01:00
ea83f43085
add README for project
2018-03-11 12:59:57 +01:00
49966cd207
add script to save models as tar archives
2018-03-10 01:07:56 +01:00
b07f075627
training and evaluation stats are now logged by default to model/logs/
2018-03-10 00:39:55 +01:00
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
bd459ba0ad
typos
2018-03-09 21:02:41 +01:00
b49946e42c
Added player type and possibility of playing against network as player
2018-03-09 14:19:31 +01:00
f3f0e40aa4
small fixes
2018-03-08 17:51:32 +01:00
150036a6cb
plot-plot
2018-03-08 17:13:25 +01:00
ef7d6eb04b
plot.py
2018-03-08 16:36:16 +01:00
