mirror of
https://github.com/jcreek/CosmicClash.git
synced 2026-09-11 00:14:00 +00:00
Josh Creek
efda6c1a05
Generation 2's first two real stage-1 attempts both independently restarted from curric-s5-aggression (reset_retry_checkpoint) with identical flags and landed at 32% and 27% win rate vs the reference -- a real regression either way, but too much spread between "identical" runs for repeat fresh restarts to be a controlled test of anything. The first attempt's own trajectory (ep_rew_mean climbing from -10.86 toward ~0 by the 240M-step cutoff, briefly touching positive) looked closer to convergence than the second's, so retries now continue that attempt's own checkpoint for another full timesteps budget instead of resetting to foundation again. Drops retry1 and retry2 (checkpoints, logs, exported bots, eval_history entries) -- retry2 never trained meaningfully before crashing on the GoalRateCallback bug just fixed, and retry1 was the inferior of the two real samples. curriculum_state.json rewinds to attempt 1, in_progress, so the next run resumes 20260726-1904-curric-s1-unmask/final.zip directly.
143 lines
4.6 KiB
JSON
143 lines
4.6 KiB
JSON
[
|
|
{
|
|
"timestamp": "2026-07-18T18:27:59+00:00",
|
|
"model_a": "/Users/jcreek/Documents/repos/GitHub/CosmicClash/Game/bots/rookie.json",
|
|
"model_b": "/Users/jcreek/Documents/repos/GitHub/CosmicClash/Game/bots/rookie.json",
|
|
"episodes": 6,
|
|
"wins_a": 1,
|
|
"wins_b": 0,
|
|
"draws": 5,
|
|
"win_rate_a": 0.167
|
|
},
|
|
{
|
|
"timestamp": "2026-07-19T12:11:30+00:00",
|
|
"model_a": "/Users/jcreek/Documents/repos/GitHub/CosmicClash/Game/bots/run01.json",
|
|
"model_b": "/Users/jcreek/Documents/repos/GitHub/CosmicClash/Game/bots/run02.json",
|
|
"episodes": 40,
|
|
"wins_a": 4,
|
|
"wins_b": 1,
|
|
"draws": 35,
|
|
"win_rate_a": 0.1
|
|
},
|
|
{
|
|
"timestamp": "2026-07-20T18:47:54+00:00",
|
|
"model_a": "/Users/jcreek/Documents/repos/GitHub/CosmicClash/Game/bots/run09.json",
|
|
"model_b": "/Users/jcreek/Documents/repos/GitHub/CosmicClash/Game/bots/run07.json",
|
|
"episodes": 40,
|
|
"wins_a": 6,
|
|
"wins_b": 9,
|
|
"draws": 25,
|
|
"win_rate_a": 0.15
|
|
},
|
|
{
|
|
"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
|
|
},
|
|
{
|
|
"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
|
|
},
|
|
{
|
|
"timestamp": "2026-07-21T20:46:34+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/curric-s3-no_draws.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/curric-s2-defend.json",
|
|
"episodes": 100,
|
|
"wins_a": 44,
|
|
"wins_b": 19,
|
|
"draws": 37,
|
|
"win_rate_a": 0.44
|
|
},
|
|
{
|
|
"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
|
|
},
|
|
{
|
|
"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
|
|
},
|
|
{
|
|
"timestamp": "2026-07-22T11:40:07+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-s2-defend.json",
|
|
"episodes": 100,
|
|
"wins_a": 24,
|
|
"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
|
|
},
|
|
{
|
|
"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
|
|
},
|
|
{
|
|
"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
|
|
},
|
|
{
|
|
"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
|
|
},
|
|
{
|
|
"timestamp": "2026-07-27T23:30:59+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260726-1904-curric-s1-unmask.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/curric-s5-aggression.json",
|
|
"episodes": 100,
|
|
"wins_a": 32,
|
|
"wins_b": 50,
|
|
"draws": 18,
|
|
"win_rate_a": 0.32
|
|
}
|
|
]
|