nora
/
asteroids-genetic
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
56 Commits 1 Branch 0 Tags 395 KiB
Commit Graph

56 Commits

Author SHA1 Message Date
Leonora Tindall c8233134c3 Use raw score for fitness 2023-04-03 23:20:27 -05:00
Leonora Tindall aebdbeb356 Add extra layer to default config 2023-04-03 23:20:27 -05:00
Leonora Tindall 5d1c1aca27 Output max, mean, median, and minimum fitness values 2023-04-03 23:20:27 -05:00
Leonora Tindall 179b503634 Let bullets wrap around the screen 
They are now killed once having travelled the entire diagonal dimension
of the screen, which removes the last dependence on "true" x/y position.
Now, only relative position matters.
 2023-04-03 23:20:23 -05:00
Leonora Tindall 007eb03050 Add shift register memory 2023-04-03 22:52:54 -05:00
Leonora Tindall e63fbf74ba Accept multiple asteroids and shot-time input 2023-04-03 22:52:45 -05:00
Leonora Tindall 36da3483ae Use a more lenient asteroid spawning strategy 
Two large asteroids are created to start.
New asteroids are only created when the total asteroid area is below 12.
Large asteroids have 4 area, medium asteroids have 2, and small
asteroids have 1.
Asteroid true sizes are based on multiples of a base number.
 2023-04-03 22:36:06 -05:00
Leonora Tindall 154517654e Improve crossover function 
Rather than always choosing a parental weight verbatim, weights are
sometimes averaged between parents.
 2023-04-03 22:34:28 -05:00
Leonora Tindall d71b437124 Permit larger layers (up to 64 neurons) 2023-04-03 22:34:05 -05:00
Leonora Tindall 49b720baec Use a normal distribution for mutations 
Rather than StandardNormal, weights are generated with a Normal
distribution centered on 0 with a standard deviation of 0.75,
and mutations are performed by adding a number from that distribution to
the existing weight, rather than replacing the weight entirely.
 2023-04-03 22:32:53 -05:00
Leonora Tindall f04309f678 Ignore testing files 2023-04-03 22:30:51 -05:00
Sparsh Goenka d0c5d7eb43
update readme 2023-01-25 03:37:29 +05:30
sparshg e50d1f4954 fullscreen, resizable = false 2023-01-24 17:50:56 +05:30
sparshg 991df7d76e test, fix raycast inputs 2023-01-15 18:31:41 +05:30
sparshg 18fd825c99 extract skins 2023-01-14 16:28:33 +05:30
sparshg 7cbfcd91af change keyboard shortcuts 2023-01-14 16:14:05 +05:30
Sparsh Goenka dfca5216ee
Update README.md 2023-01-14 16:11:47 +05:30
sparshg 50a0c51e64 max life 1min 2023-01-14 13:33:19 +05:30
Sparsh Goenka bd57af3447
Update README.md 2023-01-14 13:27:23 +05:30
sparshg d8bef225f9 optimize size 2023-01-13 13:19:45 +05:30
sparshg e4c3716f80 readme 2023-01-13 03:28:52 +05:30
sparshg a4b5323b3e include textures in binary 2023-01-13 03:07:52 +05:30
sparshg 4fae04f5cd play as human 2023-01-13 01:32:58 +05:30
sparshg 0796eda239 tracking ui 2023-01-13 00:23:40 +05:30
sparshg b7ad50da37 activ func 2023-01-12 15:25:26 +05:30
sparshg 8d317346f8 hlayers, mut_rate ui bridged 2023-01-12 03:01:03 +05:30
sparshg 39941c8425 side ui 2023-01-12 00:26:03 +05:30
sparshg b9bc8ae08d debug, selection 2023-01-10 00:55:18 +05:30
sparshg 7110d063b4 speed control 2023-01-09 02:10:34 +05:30
sparshg 31be57ab37 load/save models 2023-01-09 01:39:10 +05:30
sparshg 7255bd617d nn ui text 2023-01-09 00:56:00 +05:30
sparshg 7e3acb4d57 player visual 2023-01-09 00:37:35 +05:30
sparshg 7dea9e0406 ui bars 2023-01-08 03:29:59 +05:30
sparshg 3ce1fdb957 visuals 2023-01-07 04:17:57 +05:30
sparshg 02df5694f9 import/export models 2023-01-06 14:40:29 +05:30
sparshg b9cfedc00d cleanup 2023-01-06 02:03:25 +05:30
sparshg edf1db25e0 final tweaking 2023-01-06 01:40:35 +05:30
sparshg 1c036ec097 cleanup 2023-01-05 22:16:08 +05:30
sparshg 8196383515 finally works T_T im ded 2023-01-05 01:27:59 +05:30
sparshg 32df37e391 aim asteroids, asteroids by time, raycast inputs 2022-10-24 00:37:18 +05:30
sparshg 1c29b6d419 bug fixes 2022-10-23 01:10:19 +05:30
sparshg db2df770c6 fixed bugs 2022-10-14 16:27:58 +05:30
sparshg 666c9a8b8e pop done 2022-10-11 01:13:05 +05:30
sparshg 1f0b6e06e0 genetic algorithm 2022-10-11 00:06:14 +05:30
sparshg e66d8ff9d4 frame independent -> dependent, nn 2022-10-10 15:43:06 +05:30
sparshg 6e1b0f9d3b remove `get_frame_time()` 2022-10-10 01:42:23 +05:30
sparshg 4084a43acc population 2022-10-10 01:41:24 +05:30
sparshg 91bc4e27a4 crossover, mutation 2022-10-10 01:16:27 +05:30
sparshg 44e2cb36f4 feed_forward: Vec -> Vec 2022-10-10 00:03:00 +05:30
sparshg 80fb255c36 neural network, feed forward 2022-10-09 23:44:22 +05:30