 Connor Olding
|
c30f07f407
|
prevent reward gained from fireworks
|
2018-06-08 14:12:21 +02:00 |
|
|
Connor Olding
|
c40e1f929d
|
fix skipped inputs on lag frames
|
2018-06-08 13:48:59 +02:00 |
|
|
Connor Olding
|
912e114efe
|
update todo
|
2018-06-08 13:47:32 +02:00 |
|
|
Connor Olding
|
e24c3d31a4
|
use argsort
|
2018-06-08 13:46:38 +02:00 |
|
|
Connor Olding
|
d33bdfea62
|
add argsort function
|
2018-06-08 02:46:00 +02:00 |
|
|
Connor Olding
|
374fa4d876
|
cleanup
|
2018-06-08 02:45:07 +02:00 |
|
|
Connor Olding
|
37d404e77d
|
reduce embed layer to values actually used ingame
|
2018-06-07 22:40:31 +02:00 |
|
|
Connor Olding
|
9c8c1ccd0c
|
add tanh activation
|
2018-05-14 08:27:20 +02:00 |
|
|
Connor Olding
|
3030e83d00
|
refactor learn_from_epoch
|
2018-05-14 01:34:08 +02:00 |
|
|
Connor Olding
|
ec19774af5
|
localize a couple more things
|
2018-05-12 23:08:00 +02:00 |
|
|
Connor Olding
|
15f0292485
|
remove defer_prints option (now always true)
|
2018-05-12 22:56:04 +02:00 |
|
|
Connor Olding
|
0fb3b1780f
|
remove some old comments
|
2018-05-12 22:55:04 +02:00 |
|
|
Connor Olding
|
a836314b8b
|
refactor game and utility functions
|
2018-05-12 22:44:53 +02:00 |
|
|
Connor Olding
|
7f34de8e7c
|
add cosine activation
|
2018-05-12 21:51:00 +02:00 |
|
|
Connor Olding
|
7db43038ac
|
adjust range of timed inputs to stdev of roughly 1
|
2018-05-07 16:27:51 +02:00 |
|
|
Connor Olding
|
7357c8ed62
|
move LayerNorm after Relu
|
2018-05-07 16:22:48 +02:00 |
|
|
Connor Olding
|
e3a8a6b87f
|
tweak config
|
2018-05-07 16:22:02 +02:00 |
|
|
Connor Olding
|
946f05bd3e
|
base timed inputs on start of trial time
|
2018-05-07 16:20:59 +02:00 |
|
|
Connor Olding
|
3e7aeb3c91
|
config tweaks and fixes
|
2018-05-07 09:20:22 +02:00 |
|
|
Connor Olding
|
ce64801368
|
fix some inputs
|
2018-05-07 09:19:24 +02:00 |
|
|
Connor Olding
|
5201b75509
|
add Lipschitz heuristic/approximation
|
2018-05-07 05:57:52 +02:00 |
|
|
Connor Olding
|
ee066154b2
|
add test trial logging
|
2018-05-07 05:57:18 +02:00 |
|
|
Connor Olding
|
deb1ea7de0
|
add LayerNorm layer
|
2018-05-07 05:55:58 +02:00 |
|
|
Connor Olding
|
feaf86dc6b
|
allow weights/params file to be configured
|
2018-05-04 21:02:08 +02:00 |
|
|
Connor Olding
|
90922a2bc3
|
add AMSgrad optimizer and logging
|
2018-05-03 16:48:12 +02:00 |
|
|
Connor Olding
|
c7c657513e
|
fix softmax
|
2018-05-03 16:48:12 +02:00 |
|
|
Connor Olding
|
7831f534c9
|
tweaks
|
2018-05-03 16:48:12 +02:00 |
|
|
Connor Olding
|
2bdd67b721
|
add playback_mode
|
2018-05-03 16:48:12 +02:00 |
|
|
Connor Olding
|
b453438055
|
add graycode-like distribution option
|
2018-05-03 16:48:12 +02:00 |
|
|
Connor Olding
|
6a01f609a9
|
split strictness to its own file
|
2018-05-03 16:48:12 +02:00 |
|
|
Connor Olding
|
545618c70b
|
refactor config vars to their own files
|
2018-05-03 16:48:12 +02:00 |
|
|
Connor Olding
|
66bf689e04
|
reduce time waiting at world screen, tweak config
|
2018-05-03 16:48:12 +02:00 |
|
|
Connor Olding
|
5636c7b2ed
|
tweak config and network
|
2018-05-03 16:48:12 +02:00 |
|
|
Connor Olding
|
d696bd8c21
|
reimplement softchoice and redo noise generation
|
2018-05-03 16:45:38 +02:00 |
|
|
Connor Olding
|
bb44d6696e
|
remove backprop code
|
2018-03-26 16:33:23 +02:00 |
|
|
Connor Olding
|
5b98023073
|
experimental ARS stuff
|
2018-03-26 16:32:00 +02:00 |
|
|
Connor Olding
|
4765104c7a
|
update todo
|
2018-03-23 09:33:02 +01:00 |
|
|
Connor Olding
|
57cead431d
|
add TODOs to notice
|
2018-01-30 20:25:23 +01:00 |
|
|
Connor Olding
|
093dcf41b7
|
add notice
|
2018-01-30 19:52:40 +01:00 |
|
|
Connor Olding
|
27098141c3
|
not literally
|
2018-01-30 19:49:52 +01:00 |
|
|
Connor Olding
|
c76ec6a87c
|
more cleanup
|
2017-09-09 19:46:35 +00:00 |
|
|
Connor Olding
|
01d7e5e230
|
cleanup
|
2017-09-09 19:37:01 +00:00 |
|
|
Connor Olding
|
d384635000
|
select outputs from array instead of binary combinations
|
2017-09-08 10:43:32 +00:00 |
|
|
Connor Olding
|
88dcd203a1
|
tweaks and fixes
|
2017-09-08 10:40:19 +00:00 |
|
|
Connor Olding
|
5a8c0f6140
|
add graphviz printing and stuff
|
2017-09-07 23:06:43 +00:00 |
|
|
Connor Olding
|
acc8378980
|
add and utilize Merge and Embed layers
|
2017-09-07 23:06:30 +00:00 |
|
|
Connor Olding
|
6f2ffcdef7
|
fix frameskip stuff and give mario an extra life
|
2017-09-07 22:11:57 +00:00 |
|
|
Connor Olding
|
3b4e195ae6
|
add frameskip
|
2017-09-07 21:20:53 +00:00 |
|
|
Connor Olding
|
3d64df0574
|
preliminary batches and backwards passes
also adds negated noise trials because i forgot to commit that earlier
|
2017-09-07 19:18:11 +00:00 |
|
|
Connor Olding
|
3e3b4d9207
|
looking forwards
|
2017-09-07 19:12:58 +00:00 |
|