|
|
5c64fcf395
|
overhaul SNES (importance sampling, adaptation sampling, etc)
|
2018-06-13 01:19:32 +02:00 |
|
|
|
7bb9c79367
|
allow Dense layers without biasing
|
2018-06-13 01:02:41 +02:00 |
|
|
|
fca4779e56
|
fix training without an unperturbed trial
|
2018-06-13 01:00:15 +02:00 |
|
|
|
b7a9360d6d
|
add min_time setting (cap_time -> max_time)
|
2018-06-13 00:59:36 +02:00 |
|
|
|
7cecd57d05
|
tweak inits and norm_in for variances of 1
|
2018-06-12 23:39:13 +02:00 |
|
|
|
74eb2bfbef
|
fix antithetic ARS
|
2018-06-12 20:57:31 +02:00 |
|
|
|
ccce6a2d55
|
sigma tweaks
|
2018-06-12 05:39:22 +02:00 |
|
|
|
12098ee592
|
add normalize_sums utility function
|
2018-06-12 05:37:55 +02:00 |
|
|
|
0d28db0fc4
|
allow division of input size in Dense layers
|
2018-06-12 05:37:35 +02:00 |
|
|
|
6c554e0f49
|
use local in LayerNorm
|
2018-06-12 05:36:57 +02:00 |
|
|
|
50a7ba78f9
|
make filenames local to main
|
2018-06-12 05:36:24 +02:00 |
|
|
|
4a09280be4
|
add pdf and cdf functions
|
2018-06-11 08:11:23 +02:00 |
|
|
|
fa0287d966
|
add sigma decay; move printing to start of epoch
|
2018-06-10 19:34:17 +02:00 |
|
|
|
56f7c01256
|
fix network loading
|
2018-06-10 19:34:06 +02:00 |
|
|
|
bc655979af
|
display decisions made instead of frame count
|
2018-06-10 16:48:02 +02:00 |
|
|
|
19cd10382f
|
use experimental config/network
|
2018-06-10 16:41:45 +02:00 |
|
|
|
401effbc23
|
insignificant tweaks
|
2018-06-10 16:41:32 +02:00 |
|
|
|
70742ccf93
|
temporarily remove sprite type (it's busted anyway)
|
2018-06-10 16:41:07 +02:00 |
|
|
|
3eebbc534a
|
add SNES optimizer
|
2018-06-10 16:40:20 +02:00 |
|
|
|
d87b8e7118
|
add mean adaptation hyperparameter
|
2018-06-10 16:38:25 +02:00 |
|
|
|
47eb173dac
|
add exists utility function
|
2018-06-10 16:36:15 +02:00 |
|
|
|
771650613c
|
move dot_mv to nn
|
2018-06-10 16:34:20 +02:00 |
|
|
|
0100934ac4
|
add antithetic sampling for xNES
|
2018-06-10 16:33:38 +02:00 |
|
|
|
695730335c
|
set experimental config
|
2018-06-09 19:19:01 +02:00 |
|
|
|
d6cc49cde1
|
fix learning without negate_trials
|
2018-06-09 18:56:10 +02:00 |
|
|
|
bcb6cb9da1
|
add xNES optimizer
|
2018-06-09 18:56:10 +02:00 |
|
|
|
fe9494b0d5
|
refactor ARS out of main (breaks a bunch of stuff)
|
2018-06-09 18:56:10 +02:00 |
|
|
|
d3e6441c40
|
reduce tile input to 5 per row using new layers
|
2018-06-09 16:20:20 +02:00 |
|
|
|
dd5ec3dbde
|
make network linear
|
2018-06-09 16:20:07 +02:00 |
|
|
|
2b4bffb401
|
add Reshape and DenseBroadcast layers
|
2018-06-09 16:17:52 +02:00 |
|
|
|
ae331ce60b
|
remove remnants of backwards pass
|
2018-06-09 15:24:12 +02:00 |
|
|
|
f03e80b1b6
|
rename notice
|
2018-06-09 09:47:33 +02:00 |
|
|
|
cbb094adc9
|
restore flagpole bonus, add missing overlay check
|
2018-06-09 04:35:09 +02:00 |
|
|
|
9fb98d3fe0
|
allow setting of world-level, plus random option
|
2018-06-09 04:34:21 +02:00 |
|
|
|
81d6b509d0
|
detect when mario is controllable
|
2018-06-09 01:43:22 +02:00 |
|
|
|
5f85b92b6d
|
simplify gameconfig button specification
|
2018-06-08 23:59:55 +02:00 |
|
|
|
9b23327df4
|
add score multiplier
|
2018-06-08 23:59:43 +02:00 |
|
|
|
431a591481
|
fix offscreen sprites sometimes being visible
|
2018-06-08 15:03:09 +02:00 |
|
|
|
f576a47282
|
make sprite inputs relative to center of screen
|
2018-06-08 14:52:04 +02:00 |
|
|
|
fec148fb79
|
don't turbo in playable mode, note overlay bug
|
2018-06-08 14:51:17 +02:00 |
|
|
|
c30f07f407
|
prevent reward gained from fireworks
|
2018-06-08 14:12:21 +02:00 |
|
|
|
c40e1f929d
|
fix skipped inputs on lag frames
|
2018-06-08 13:48:59 +02:00 |
|
|
|
912e114efe
|
update todo
|
2018-06-08 13:47:32 +02:00 |
|
|
|
e24c3d31a4
|
use argsort
|
2018-06-08 13:46:38 +02:00 |
|
|
|
d33bdfea62
|
add argsort function
|
2018-06-08 02:46:00 +02:00 |
|
|
|
374fa4d876
|
cleanup
|
2018-06-08 02:45:07 +02:00 |
|
|
|
37d404e77d
|
reduce embed layer to values actually used ingame
|
2018-06-07 22:40:31 +02:00 |
|
|
|
9c8c1ccd0c
|
add tanh activation
|
2018-05-14 08:27:20 +02:00 |
|
|
|
3030e83d00
|
refactor learn_from_epoch
|
2018-05-14 01:34:08 +02:00 |
|
|
|
ec19774af5
|
localize a couple more things
|
2018-05-12 23:08:00 +02:00 |
|
