jcreek/CosmicClash
1
0
Fork 0
mirror of https://github.com/jcreek/CosmicClash.git synced 2026-09-10 16:04:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore(training): curriculum progress after curric-s5-aggression

Browse Source
This commit is contained in:
CosmicClash Training Bot
2026-07-22 20:33:07 +01:00
parent fda784d50d
commit 2de3085f13
2 changed files with 29 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
training/curriculum_state.json
+19 -3
View File
@@ -1,5 +1,5 @@
{
"stage_index": 4,
"stage_index": 5,
"attempt": 0,
"status": "in_progress",
"log": [
@@ -50,7 +50,7 @@
"win_rate_a": 0.26
},
"decision": "fail",
"note": "Original eval (44-19, recorded 2026-07-21T20:46:34) predates the locomotion-mask inference bugfix (8c15c46) and ran with the grounded stage-2 reference unfairly unmasked. Re-run post-fix with --grounded-b reverses the verdict: stage 3's full-3D unmask is a clear regression from stage 2, not an improvement. Not retried via the normal flag-retry mechanism — see stage_index 4 (aggression), which redirects around this branch by resuming from curric-s2-defend directly instead."
"note": "Original eval (44-19, recorded 2026-07-21T20:46:34) predates the locomotion-mask inference bugfix (8c15c46) and ran with the grounded stage-2 reference unfairly unmasked. Re-run post-fix with --grounded-b reverses the verdict: stage 3's full-3D unmask is a clear regression from stage 2, not an improvement. Not retried via the normal flag-retry mechanism \u2014 see stage_index 4 (aggression), which redirects around this branch by resuming from curric-s2-defend directly instead."
},
{
"stage_index": 3,
@@ -67,7 +67,23 @@
"win_rate_a": 0.26
},
"decision": "pass",
"note": "Passes only against its own (already-regressed) predecessor, curric-s3-no_draws. Evaluated directly against grounded curric-s2-defend (2026-07-22T11:40:07), curric-s4-mechanics also loses clearly: 24-57-19. Do not treat this stage's 'pass' as evidence curric-s4-mechanics is the strongest available model overall — see stage 2's note and stage_index 4 (aggression)."
"note": "Passes only against its own (already-regressed) predecessor, curric-s3-no_draws. Evaluated directly against grounded curric-s2-defend (2026-07-22T11:40:07), curric-s4-mechanics also loses clearly: 24-57-19. Do not treat this stage's 'pass' as evidence curric-s4-mechanics is the strongest available model overall \u2014 see stage 2's note and stage_index 4 (aggression)."
},
{
"stage_index": 4,
"experiment": "curric-s5-aggression",
"attempt": 0,
"eval": {
"timestamp": "2026-07-22T19:33:07+00:00",
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/curric-s5-aggression.json",
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/curric-s2-defend.json",
"episodes": 100,
"wins_a": 41,
"wins_b": 47,
"draws": 12,
"win_rate_a": 0.41
},
"decision": "pass"
}
]
}
training/eval_history.json
+10
View File
@@ -88,5 +88,15 @@
"wins_b": 57,
"draws": 19,
"win_rate_a": 0.24
},
{
"timestamp": "2026-07-22T19:33:07+00:00",
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/curric-s5-aggression.json",
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/curric-s2-defend.json",
"episodes": 100,
"wins_a": 41,
"wins_b": 47,
"draws": 12,
"win_rate_a": 0.41
}
]