Commit graph

199 commits

Author SHA1 Message Date
Henri Bourcereau 088124fad1 feat: wip bot burn ppo 2025-08-19 17:46:22 +02:00
Henri Bourcereau fcd50bc0f2 refacto: bot directories 2025-08-19 16:27:37 +02:00
Henri Bourcereau e66921fcce refact models paths 2025-08-18 17:44:01 +02:00
Henri Bourcereau 2499c3377f refact script train bot 2025-08-17 17:42:59 +02:00
Henri Bourcereau a7aa087b18 fix: train bad move 2025-08-17 16:14:06 +02:00
Henri Bourcereau 1dc29d0ff0 chore:refacto clippy 2025-08-17 15:59:53 +02:00
Henri Bourcereau db9560dfac fix dqn burn small 2025-08-16 21:47:12 +02:00
Henri Bourcereau 47a8502b63 fix validations & client_cli 2025-08-16 17:59:00 +02:00
Henri Bourcereau c1e99a5f35 wip (tests fails) 2025-08-16 16:39:25 +02:00
Henri Bourcereau 56d155b911 wip debug 2025-08-16 11:13:31 +02:00
Henri Bourcereau d313cb6151 burnrl_big like before 2025-08-15 21:08:23 +02:00
Henri Bourcereau 93624c425d wip burnrl_big 2025-08-15 18:39:09 +02:00
Henri Bourcereau 86a67ae66a fix: train bot opponent rewards 2025-08-13 18:08:35 +02:00
Henri Bourcereau ac14341cf9 doc: schema store 2025-08-13 15:29:04 +02:00
Henri Bourcereau cfc19e6064 compile ok but diverge 2025-08-12 21:56:52 +02:00
Henri Bourcereau ec6ae26d38 wip reduction TrictracAction 2025-08-12 17:56:41 +02:00
Henri Bourcereau 5370eb4307 Merge branch 'feature/botTrainValidMoves' into develop 2025-08-11 18:56:17 +02:00
Henri Bourcereau bfd2a4ed47 burn-rl with valid moves 2025-08-11 18:53:45 +02:00
Henri Bourcereau 4353ba2bd1 doc params train bot 2025-08-10 21:49:15 +02:00
Henri Bourcereau 1fb04209f5 doc params train bot 2025-08-10 17:46:09 +02:00
Henri Bourcereau 778ac1817b script train bots 2025-08-10 15:35:12 +02:00
Henri Bourcereau e4b3092018 train burn-rl with integers 2025-08-10 08:39:31 +02:00
Henri Bourcereau 5b02293221 Merge branch 'feature/botBlackStrategy' into develop 2025-08-08 21:32:09 +02:00
Henri Bourcereau 17d29b8633 runcli with bot dqn burn-rl 2025-08-08 21:31:56 +02:00
Henri Bourcereau a19c5d8596 refact dqn simple 2025-08-08 18:58:21 +02:00
Henri Bourcereau 1b58ca4ccc refact dqn burn demo 2025-08-08 17:07:34 +02:00
Henri Bourcereau bf820ecc4e feat: bot random strategy 2025-08-08 16:24:40 +02:00
Henri Bourcereau b02ce8d185 fix dqn strategy color 2025-08-07 21:03:53 +02:00
Henri Bourcereau dc80243a1a fix black moves 2025-08-07 21:03:53 +02:00
Henri Bourcereau 12004ec4f3 wip bot mirror 2025-08-07 21:03:53 +02:00
Henri Bourcereau fa9c02084a doc uml diagrams 2025-08-04 12:02:12 +02:00
Henri Bourcereau fc9733b729 doc train bot results 2025-08-03 22:16:28 +02:00
Henri Bourcereau 744a70cf1d bot train graph 2025-08-03 20:32:06 +02:00
Henri Bourcereau c0d42a0c45 réglages train bot dqn burnrl 2025-08-03 16:11:45 +02:00
Henri Bourcereau 28c2aa836f fix: train bot dqn burnrl : extract config 2025-08-02 12:42:32 +02:00
Henri Bourcereau ad5ae17168 fix: check moves possibles : prevent the move of the same checker twice 2025-08-02 12:41:52 +02:00
Henri Bourcereau 2e0a874879 refacto 2025-08-01 20:45:57 +02:00
Henri Bourcereau ad58c0ec60 fix build trainbot 2025-08-01 14:21:48 +02:00
Henri Bourcereau fd269b491d wip stackoverflow debug 2025-07-28 14:03:14 +02:00
Henri Bourcereau 3e1775428d action mask 2025-07-27 09:35:30 +02:00
Henri Bourcereau cb30fd3229 fix: overflow when incrementing dice_roll_count 2025-07-25 17:41:48 +02:00
Henri Bourcereau b92c9eb7ff fix: convert_action from_action_index 2025-07-25 17:26:02 +02:00
Henri Bourcereau 1e18b784d1 load inference model 2025-07-23 21:52:32 +02:00
Henri Bourcereau f3fc053dbd save inference model 2025-07-23 21:28:29 +02:00
Henri Bourcereau 6fa8a31cc7 refact : save model 2025-07-23 21:16:28 +02:00
Henri Bourcereau c6d33555ec wip 2025-07-23 17:25:05 +02:00
Henri Bourcereau 354dcfd341 wip burn-rl dqn example 2025-07-08 21:58:15 +02:00
Henri Bourcereau b98a135749 fix: tensor dimensions
fix execution error
2025-06-29 11:30:34 +02:00
Henri Bourcereau 6a7b1cbebc fix by gemini 2025-06-28 22:18:39 +02:00
Henri Bourcereau f05094b2d4 wip 2025-06-28 21:34:44 +02:00