mirror of
https://github.com/jcreek/CosmicClash.git
synced 2026-09-10 16:04:04 +00:00
138 lines
4.9 KiB
JSON
138 lines
4.9 KiB
JSON
{
|
|
"stage_index": 5,
|
|
"attempt": 2,
|
|
"status": "blocked",
|
|
"log": [
|
|
{
|
|
"stage_index": 0,
|
|
"experiment": "curric-s1-score",
|
|
"attempt": 0,
|
|
"eval": {
|
|
"timestamp": "2026-07-21T15:52:20+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/curric-s1-score.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/rookie.json",
|
|
"episodes": 100,
|
|
"wins_a": 22,
|
|
"wins_b": 16,
|
|
"draws": 62,
|
|
"win_rate_a": 0.22
|
|
},
|
|
"decision": "pass"
|
|
},
|
|
{
|
|
"stage_index": 1,
|
|
"experiment": "curric-s2-defend",
|
|
"attempt": 0,
|
|
"eval": {
|
|
"timestamp": "2026-07-21T18:19:44+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/curric-s2-defend.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/curric-s1-score.json",
|
|
"episodes": 100,
|
|
"wins_a": 23,
|
|
"wins_b": 16,
|
|
"draws": 61,
|
|
"win_rate_a": 0.23
|
|
},
|
|
"decision": "pass"
|
|
},
|
|
{
|
|
"stage_index": 2,
|
|
"experiment": "curric-s3-no_draws",
|
|
"attempt": 0,
|
|
"eval": {
|
|
"timestamp": "2026-07-22T11:36:42+00:00",
|
|
"model_a": "/Users/jcreek/Documents/repos/GitHub/CosmicClash/Game/bots/curric-s3-no_draws.json",
|
|
"model_b": "/Users/jcreek/Documents/repos/GitHub/CosmicClash/Game/bots/curric-s2-defend.json",
|
|
"episodes": 100,
|
|
"wins_a": 26,
|
|
"wins_b": 60,
|
|
"draws": 14,
|
|
"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 \u2014 see stage_index 4 (aggression), which redirects around this branch by resuming from curric-s2-defend directly instead."
|
|
},
|
|
{
|
|
"stage_index": 3,
|
|
"experiment": "curric-s4-mechanics",
|
|
"attempt": 0,
|
|
"eval": {
|
|
"timestamp": "2026-07-22T11:38:57+00:00",
|
|
"model_a": "/Users/jcreek/Documents/repos/GitHub/CosmicClash/Game/bots/curric-s4-mechanics.json",
|
|
"model_b": "/Users/jcreek/Documents/repos/GitHub/CosmicClash/Game/bots/curric-s3-no_draws.json",
|
|
"episodes": 100,
|
|
"wins_a": 26,
|
|
"wins_b": 33,
|
|
"draws": 41,
|
|
"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 \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"
|
|
},
|
|
{
|
|
"stage_index": 5,
|
|
"experiment": "curric-s6-unmask",
|
|
"attempt": 0,
|
|
"eval": {
|
|
"timestamp": "2026-07-24T01:25:37+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/curric-s6-unmask.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/curric-s5-aggression.json",
|
|
"episodes": 100,
|
|
"wins_a": 25,
|
|
"wins_b": 50,
|
|
"draws": 25,
|
|
"win_rate_a": 0.25
|
|
},
|
|
"decision": "fail"
|
|
},
|
|
{
|
|
"stage_index": 5,
|
|
"experiment": "curric-s6-unmask-retry1",
|
|
"attempt": 1,
|
|
"eval": {
|
|
"timestamp": "2026-07-25T06:41:43+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/curric-s6-unmask-retry1.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/curric-s5-aggression.json",
|
|
"episodes": 100,
|
|
"wins_a": 20,
|
|
"wins_b": 61,
|
|
"draws": 19,
|
|
"win_rate_a": 0.2
|
|
},
|
|
"decision": "fail"
|
|
},
|
|
{
|
|
"stage_index": 5,
|
|
"experiment": "curric-s6-unmask-retry2",
|
|
"attempt": 2,
|
|
"eval": {
|
|
"timestamp": "2026-07-26T12:08:35+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/curric-s6-unmask-retry2.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/curric-s5-aggression.json",
|
|
"episodes": 100,
|
|
"wins_a": 15,
|
|
"wins_b": 68,
|
|
"draws": 17,
|
|
"win_rate_a": 0.15
|
|
},
|
|
"decision": "fail"
|
|
}
|
|
]
|
|
}
|