 Connor Olding
|
63583789c3
|
use locals; fix fitness_shaping and graycode
|
2018-06-13 22:52:37 +02:00 |
|
|
Connor Olding
|
1fba61e1b9
|
one more attempt at fixing the preset argument
|
2018-06-13 22:46:31 +02:00 |
|
|
Connor Olding
|
6498b4143f
|
tweak inputs: add power-up status, remove top/bottom tile rows
|
2018-06-13 20:18:10 +02:00 |
|
|
Connor Olding
|
6fa042eda5
|
fix preset failing to default
|
2018-06-13 06:08:32 +02:00 |
|
|
Connor Olding
|
7800510d1f
|
add xNES preset, add options, allow preset specified by argument
|
2018-06-13 03:01:54 +02:00 |
|
|
Connor Olding
|
403127bd66
|
log decisions counter
|
2018-06-13 03:00:05 +02:00 |
|
|
Connor Olding
|
b4e49d08b9
|
restore step logging, remove adamant (for now)
|
2018-06-13 01:42:36 +02:00 |
|
|
Connor Olding
|
5c64fcf395
|
overhaul SNES (importance sampling, adaptation sampling, etc)
|
2018-06-13 01:19:32 +02:00 |
|
|
Connor Olding
|
fca4779e56
|
fix training without an unperturbed trial
|
2018-06-13 01:00:15 +02:00 |
|
|
Connor Olding
|
b7a9360d6d
|
add min_time setting (cap_time -> max_time)
|
2018-06-13 00:59:36 +02:00 |
|
|
Connor Olding
|
ccce6a2d55
|
sigma tweaks
|
2018-06-12 05:39:22 +02:00 |
|
|
Connor Olding
|
0d28db0fc4
|
allow division of input size in Dense layers
|
2018-06-12 05:37:35 +02:00 |
|
|
Connor Olding
|
50a7ba78f9
|
make filenames local to main
|
2018-06-12 05:36:24 +02:00 |
|
|
Connor Olding
|
fa0287d966
|
add sigma decay; move printing to start of epoch
|
2018-06-10 19:34:17 +02:00 |
|
|
Connor Olding
|
56f7c01256
|
fix network loading
|
2018-06-10 19:34:06 +02:00 |
|
|
Connor Olding
|
bc655979af
|
display decisions made instead of frame count
|
2018-06-10 16:48:02 +02:00 |
|
|
Connor Olding
|
19cd10382f
|
use experimental config/network
|
2018-06-10 16:41:45 +02:00 |
|
|
Connor Olding
|
401effbc23
|
insignificant tweaks
|
2018-06-10 16:41:32 +02:00 |
|
|
Connor Olding
|
3eebbc534a
|
add SNES optimizer
|
2018-06-10 16:40:20 +02:00 |
|
|
Connor Olding
|
d87b8e7118
|
add mean adaptation hyperparameter
|
2018-06-10 16:38:25 +02:00 |
|
|
Connor Olding
|
47eb173dac
|
add exists utility function
|
2018-06-10 16:36:15 +02:00 |
|
|
Connor Olding
|
0100934ac4
|
add antithetic sampling for xNES
|
2018-06-10 16:33:38 +02:00 |
|
|
Connor Olding
|
d6cc49cde1
|
fix learning without negate_trials
|
2018-06-09 18:56:10 +02:00 |
|
|
Connor Olding
|
bcb6cb9da1
|
add xNES optimizer
|
2018-06-09 18:56:10 +02:00 |
|
|
Connor Olding
|
fe9494b0d5
|
refactor ARS out of main (breaks a bunch of stuff)
|
2018-06-09 18:56:10 +02:00 |
|
|
Connor Olding
|
d3e6441c40
|
reduce tile input to 5 per row using new layers
|
2018-06-09 16:20:20 +02:00 |
|
|
Connor Olding
|
dd5ec3dbde
|
make network linear
|
2018-06-09 16:20:07 +02:00 |
|
|
Connor Olding
|
cbb094adc9
|
restore flagpole bonus, add missing overlay check
|
2018-06-09 04:35:09 +02:00 |
|
|
Connor Olding
|
9fb98d3fe0
|
allow setting of world-level, plus random option
|
2018-06-09 04:34:21 +02:00 |
|
|
Connor Olding
|
81d6b509d0
|
detect when mario is controllable
|
2018-06-09 01:43:22 +02:00 |
|
|
Connor Olding
|
9b23327df4
|
add score multiplier
|
2018-06-08 23:59:43 +02:00 |
|
|
Connor Olding
|
fec148fb79
|
don't turbo in playable mode, note overlay bug
|
2018-06-08 14:51:17 +02:00 |
|
|
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
|
e24c3d31a4
|
use argsort
|
2018-06-08 13:46:38 +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
|
3030e83d00
|
refactor learn_from_epoch
|
2018-05-14 01:34:08 +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
|
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
|
946f05bd3e
|
base timed inputs on start of trial time
|
2018-05-07 16:20:59 +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 |
|