Commit Graph

47 Commits (master)

Author SHA1 Message Date
Ruben Seitz fa2acdcecd epsilon greedy > 85% 2025-12-10 14:47:19 +01:00
Ruben-FreddyLoafers 476b67fa71 status quo 2025-12-10 12:09:15 +01:00
Ruben-FreddyLoafers ec2060c375 VQ done???? 2025-12-09 13:49:17 +01:00
Ruben-FreddyLoafers f623d1375c finally fucking did pacman 2025-12-09 11:05:37 +01:00
Ruben-FreddyLoafers 3fb0afd80e stuff persistent 2025-12-08 15:15:42 +01:00
Ruben-FreddyLoafers c88d8d003e renamed vector quantization variables for readability 2025-12-08 14:57:49 +01:00
Ruben-FreddyLoafers 0798236e26 stared at the screen for 2h 2025-12-08 11:30:42 +01:00
Ruben-FreddyLoafers a73d88737e restructured filesystem 2025-12-08 09:39:52 +01:00
Ruben Seitz 8257062dc3 First implementation of VQ 2025-12-07 14:49:03 +01:00
Ruben-FreddyLoafers a53583b1d7 actually implemented that RL 2025-12-02 12:02:04 +01:00
Ruben-FreddyLoafers a891d51ca9 commencing with actual reinforcement learning 2025-12-01 15:16:34 +01:00
Ruben Seitz 48a351518d good enough i guess 2025-11-27 16:09:47 +01:00
Ruben Seitz 85f81e5f23 pacman works; commencing finetuning 2025-11-27 16:01:04 +01:00
Ruben Seitz 8049bfe29f removed 0's; set q[s][a]=-10 at the right place 2025-11-24 21:56:57 +01:00
Ruben-FreddyLoafers ad40c248d3 Keep fighting 2025-11-24 21:03:19 +01:00
Ruben Seitz a76d2c41d3 added max iterations 2025-11-24 11:24:27 +01:00
Ruben Seitz 1453fd930a debugging reward system 2025-11-24 10:22:34 +01:00
Ruben Seitz 8bd97eb9ef done did it again not 2025-11-20 18:57:35 +01:00
Ruben-FreddyLoafers 6c9a096b61 mental breakdown 2025-11-20 15:32:28 +01:00
Ruben-FreddyLoafers 6f7dcb8326 debugging 2025-11-19 20:03:21 +01:00
Ruben Seitz ee04e00627 tried a couple things out; Balancing reward system 2025-11-19 13:59:41 +01:00
Ruben-FreddyLoafers 24714fca0e removed impossible states; better distance consideration; bug fixing 2025-11-18 14:42:43 +01:00
Ruben Seitz a7b43c9037 logic done; debugging commencing 2025-11-17 14:52:36 +01:00
Ruben-FreddyLoafers 469d1d1a47 ASs 4 started 2025-11-13 13:54:32 +01:00
Ruben-FreddyLoafers 1df2ad190a ass 3 done!! 2025-11-05 10:50:27 +01:00
Ruben-FreddyLoafers c9869979d3 assignment 3 done? 2025-11-05 10:09:22 +01:00
Ruben-FreddyLoafers cf9131b760 implemented taylor stuff 2025-10-28 20:24:52 +01:00
Ruben-FreddyLoafers 4de71f8850 code cleanup 2025-10-28 15:48:52 +01:00
Ruben-FreddyLoafers 9a61a7f1d6 finished?? 2025-10-28 15:41:22 +01:00
Ruben-FreddyLoafers f95f848b22 updated .gitignore 2025-10-28 12:22:39 +01:00
Ruben-FreddyLoafers ad7f706c90 fixed selection; static population size; fixed whitespaces in bits 2025-10-28 12:20:58 +01:00
Ruben-FreddyLoafers ed8c880c81 fixing sleection WIP 2025-10-22 16:18:41 +02:00
Ruben-FreddyLoafers c865008f0e further debugging 2025-10-20 16:34:08 +02:00
Ruben-FreddyLoafers 4028d11de1 started debugging lol 2025-10-20 13:29:23 +02:00
Ruben-FreddyLoafers 6547edc23e mutate function done? 2025-10-20 12:56:15 +02:00
Ruben-FreddyLoafers a6b906d9b3 improved code structure; fitness evaluation done; selection done 2025-10-16 14:23:15 +02:00
Ruben-FreddyLoafers bc1ffb957a done did it again 2025-10-15 15:22:05 +02:00
Ruben-FreddyLoafers 839f023ee8 creating params 2025-10-13 15:16:26 +02:00
Ruben-FreddyLoafers e67b8fd702 made functions more cheap 2025-10-13 13:30:41 +02:00
Ruben-FreddyLoafers 4a8b78bc80 grey to bin and bin to grey progress 2025-10-13 13:27:05 +02:00
Ruben-FreddyLoafers 79800b9907 started with gn_alg 2025-10-12 18:04:41 +02:00
Ruben-FreddyLoafers 3bf9ec3d2e adjusted temperature in assignment 2 2025-10-08 10:45:02 +02:00
Ruben-FreddyLoafers f8b889c213 Adjusted assignment 1 and 2 2025-10-08 10:15:36 +02:00
Ruben-FreddyLoafers 27ca92b80b Added .gitignore 2025-10-06 12:52:06 +02:00
Ruben Seitz b478119660 finished simulated annealing 2025-10-05 15:59:52 +02:00
Ruben Seitz b68e2fcfc3 Finished Hillclimber algorithm 2025-10-05 14:40:38 +02:00
Ruben Seitz c96abad68f Wannabe Hill-Climber implemented 2025-10-05 14:19:44 +02:00