49dfcfe5b3
scale param decay by sigma (prevents unlearning?)
2018-06-16 22:47:57 +02:00
31f153aec0
add video link
2018-06-16 01:01:24 +02:00
7a5ba49356
don't turbo in playback mode
2018-06-16 00:55:41 +02:00
c3929d8aa1
remove some ancient useless code
2018-06-16 00:55:41 +02:00
2fe009b5fe
don't base max_time on number of trials (fixes playback mode)
2018-06-16 00:55:41 +02:00
b0058db80e
TODOs and delete an unused variable
2018-06-16 00:38:09 +02:00
155f868f56
another attempt at fixing preset argument
2018-06-16 00:37:19 +02:00
e3695bfb84
rename weight* to param* outside of nn.lua
2018-06-16 00:33:47 +02:00
f3fc95404c
overhaul learning rates:
...
- rename mean_adapt to weight_rate
- sigma and covar update rates can be specified separately
(sigma_rate, covar_rate)
- base decays on current rates instead of initially configured rates
(this might break stuff)
- base_rate takes the place of learning_rate
2018-06-16 00:29:15 +02:00
474bac45b8
update xnes2 preset with better sample efficiency
2018-06-16 00:06:58 +02:00
655cb6f5b3
add snes2 xnes2 presets, cleanup, tweaks etc.
2018-06-14 22:42:51 +02:00
33eeaf9c76
cleanup
2018-06-14 22:40:52 +02:00
f512f8ac3a
add sigma decay to xNES
2018-06-14 22:40:39 +02:00
422468dd47
more comments
2018-06-14 22:15:49 +02:00
63583789c3
use locals; fix fitness_shaping and graycode
2018-06-13 22:52:37 +02:00
a1ec797de0
add playable preset
2018-06-13 22:46:57 +02:00
1fba61e1b9
one more attempt at fixing the preset argument
2018-06-13 22:46:31 +02:00
ac4c534185
fix non-antithetic case for ARS
2018-06-13 22:46:09 +02:00
601d78bfda
add evaluation counting to ARS, cleanup
2018-06-13 21:54:04 +02:00
6498b4143f
tweak inputs: add power-up status, remove top/bottom tile rows
2018-06-13 20:18:10 +02:00
6fa042eda5
fix preset failing to default
2018-06-13 06:08:32 +02:00
46f1020bfa
fix xNES telling
2018-06-13 03:01:54 +02:00
7800510d1f
add xNES preset, add options, allow preset specified by argument
2018-06-13 03:01:54 +02:00
403127bd66
log decisions counter
2018-06-13 03:00:05 +02:00
719edfa4ae
remove unused functions from config
2018-06-13 02:07:14 +02:00
b8a197eae4
add usage instructions
2018-06-13 02:03:26 +02:00
16acc68850
add presets to config, update config in general
2018-06-13 02:02:56 +02:00
b4e49d08b9
restore step logging, remove adamant (for now)
2018-06-13 01:42:36 +02:00
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
