d426c1c3b5
tesauro fat and diffs in values
2018-05-22 15:10:41 +02:00
c31bc39780
More server
2018-05-22 00:26:32 +02:00
6133cb439f
Merge remote-tracking branch 'origin/experimentation' into experimentation
2018-05-20 20:15:57 +02:00
5acd79b6da
Slight modification to move calculation
2018-05-20 19:43:28 +02:00
=
b11e783b30
add 0-ply-tests
2018-05-20 18:50:28 +02:00
f834b10e02
remove unnecessary print
2018-05-20 16:52:05 +02:00
72f01a2a2d
remove dependency on yaml
2018-05-20 16:03:58 +02:00
d14e6c5994
Everything might work, except for quad, that might be bugged.
2018-05-20 00:38:13 +02:00
a266293ecd
Stuff is happening, moving is better!
2018-05-19 22:01:55 +02:00
e9a46c79df
server and stuff
2018-05-19 14:12:13 +02:00
816cdfae00
fix and clean
2018-05-18 14:55:10 +02:00
3e379b40c4
Accidentally added a '5' in the middle of a variable.
2018-05-16 00:20:54 +02:00
90fad334b9
More optimizations.
2018-05-15 23:37:35 +02:00
a77c13a0a4
1-ply runs even faster.
2018-05-15 19:29:27 +02:00
260c32d909
oiuhhiu
2018-05-15 18:16:44 +02:00
00974b0f11
Added '--play' flag, so you can now play against the ai.
2018-05-14 13:07:48 +02:00
2c02689577
Merge remote-tracking branch 'origin/eager_eval' into eager_eval
2018-05-13 23:55:02 +02:00
926a331df0
Some flags from main.py is gone, rolls now allow a face_value of 0 yet
...
again and it is possible to play against the ai. There is no flag
for this yet, so this has to be added.
2018-05-13 23:54:13 +02:00
d932663519
add explanation of ply speedup
2018-05-13 22:26:24 +02:00
2312c9cb2a
Merge branch 'eager_eval' of gitfub.space:Pownie/backgammon into eager_eval
2018-05-12 15:19:12 +02:00
9f1bd56c0a
fix bear_off bug; addtional tests and additional fixes
2018-05-12 15:18:52 +02:00
ba4ef86bb5
Board rep can now be inferred from file after being given once.
...
We can also evaluate multiple times by using the flag "--repeat-eval".
The flag defaults to 1, if not provided.
2018-05-12 12:14:47 +02:00
c3f5e909d6
flip is back
2018-05-11 21:47:48 +02:00
1aa9cf705f
quack without leaks
2018-05-11 21:24:10 +02:00
383dd7aa4b
code works again; quack gave ~3 times improvement for calc_moves
2018-05-11 20:13:43 +02:00
93188fe06b
more quack for board
2018-05-11 20:07:27 +02:00
ffbc98e1a2
quack kind of works
2018-05-11 19:00:39 +02:00
03e61a59cf
quack
2018-05-11 17:29:22 +02:00
93224864a4
More comments, backprop have been somewhat tested in the eager_main.py
...
and normal_main.py.
2018-05-11 13:35:01 +02:00
504308a9af
Yet another input argument, "--ply", 0 for no look-ahead, 1 for a single
...
look-ahead.
2018-05-10 23:22:41 +02:00
3b57c10b5a
Saves calling tf.reduce_mean on all values once.
2018-05-10 22:57:27 +02:00
4fa10861bb
update TF dependency to 1.8.0
2018-05-10 19:27:51 +02:00
6131d5b5f4
Added comments for Christoffer!
2018-05-10 19:25:28 +02:00
1aedc23de1
1-ply now works again.
2018-05-10 19:13:18 +02:00
2d84cd5a0b
1-ply now works again.
2018-05-10 19:06:53 +02:00
396d5b036d
All values for boards and all rolls can now be calculated
2018-05-10 18:41:21 +02:00
4efb229d34
Added a lot of comments
2018-05-10 15:28:33 +02:00
f2a67ca92e
All board reps should now work as input.
2018-05-10 10:49:25 +02:00
9cfdd7e2b2
Added a verbosity flag, --verbose, which allows for printing of
...
variables and such.
2018-05-10 10:39:22 +02:00
6429e0732c
We should now be able to both train and eval as per usual.
...
I've added a file "global_step", which works as the new global_step
counter, so we can use it for exp_decay.
2018-05-09 23:15:35 +02:00
cb7e7b519c
Getting closer to functionality. We're capable of evaluating moves
...
and a rework of global_step has begun, such that we now use
episode_count as a way of calculating exp_decay, which have been
implemented as a function.
2018-05-09 22:22:12 +02:00
9a2d87516e
Ongoing rewrite of network to use an eager model. We're now capable of
...
evaluating a list of states with network.py. We can also save and
restore models.
2018-05-09 00:33:05 +02:00
7b308be4e2
Different implementations of different speed
2018-05-07 22:24:47 +02:00
ac6660e05b
Added board-rep as cli argument, to state which input-board-rep to use.
...
Also fixed weird nesting of difference_in_values.
2018-05-06 20:52:35 +02:00
1f8485f54e
No longer use n_ply, shit's too slow man.
...
Added extra logging, now logs the average difference in values
between trainings.
Also fixed bug with the length of quack-norm.
Also added cli argument; use-baseline, if set, the baseline-model
will be used.
2018-05-06 20:41:07 +02:00
1db469709a
make_move now calls n_ply to search deeper and potentially give
...
better moves. It's hella fucking slow.
2018-05-02 01:06:23 +02:00
695a3d43db
Fixed n_ply and actually added a comma in main.py. *clap Christoffer*
2018-05-01 20:39:29 +02:00
c530aa688d
flipidip
2018-05-01 13:48:42 +02:00
3f6849048e
added network_test and some comments
2018-04-29 12:14:14 +02:00
afa6504b05
ply again again
2018-04-26 16:49:49 +02:00
