donkeycar-rl-autoresearch/agent/models/eval_gentrack_minimonaco_20...

48 lines
2.7 KiB
Plaintext

[18:43:05] ======================================================================
[18:43:05] Eval: generated-track specialists on mini-monaco (zero-shot)
[18:43:05] Track : donkey-minimonaco-track-v0
[18:43:05] Episodes: 7 x max 2000 steps
[18:43:05] Host : localhost:9091
[18:43:05] Log : /home/paulh/projects/donkeycar-rl-autoresearch/agent/models/eval_gentrack_minimonaco_20260506_184305.log
[18:43:05] ======================================================================
[18:43:05]
[18:43:05] ── exp13-gentrack-v4 ──────────────────────────────────────
[18:43:05] Model: /home/paulh/projects/donkeycar-rl-autoresearch/agent/models/exp13-gentrack-v4/best_model.zip
[18:43:12] ep1: 4.5r / 29s ❌@29
[18:43:15] ep2: 4.5r / 28s ❌@28
[18:43:18] ep3: 4.6r / 28s ❌@28
[18:43:21] ep4: 4.7r / 28s ❌@28
[18:43:24] ep5: 4.6r / 28s ❌@28
[18:43:27] ep6: 4.6r / 28s ❌@28
[18:43:30] ep7: 4.6r / 28s ❌@28
[18:43:31] SUMMARY: 0/7 full | mean 28s / 4.6r | ❌ CRASHES
[18:43:33]
[18:43:33] ── wave5-gentrack-only ──────────────────────────────────────
[18:43:33] Model: /home/paulh/projects/donkeycar-rl-autoresearch/agent/models/wave5-gentrack-only/model.zip
[18:43:36] ep1: 4.8r / 28s ❌@28
[18:43:39] ep2: 4.7r / 28s ❌@28
[18:43:42] ep3: 4.9r / 28s ❌@28
[18:43:45] ep4: 4.7r / 28s ❌@28
[18:43:49] ep5: 4.6r / 27s ❌@27
[18:43:52] ep6: 4.9r / 28s ❌@28
[18:43:55] ep7: 4.9r / 28s ❌@28
[18:43:55] SUMMARY: 0/7 full | mean 28s / 4.8r | ❌ CRASHES
[18:43:57]
[18:43:57] ── wave4-trial-0009 ──────────────────────────────────────
[18:43:57] Model: /home/paulh/projects/donkeycar-rl-autoresearch/agent/models/wave4-trial-0009/model.zip
[18:44:01] ep1: 4.9r / 28s ❌@28
[18:44:04] ep2: 5.3r / 28s ❌@28
[18:44:07] ep3: 5.1r / 28s ❌@28
[18:44:10] ep4: 5.0r / 29s ❌@29
[18:44:13] ep5: 5.1r / 28s ❌@28
[18:44:16] ep6: 5.3r / 29s ❌@29
[18:44:19] ep7: 5.3r / 29s ❌@29
[18:44:19] SUMMARY: 0/7 full | mean 28s / 5.1r | ❌ CRASHES
[18:44:21]
[18:44:21] ======================================================================
[18:44:21] FINAL RESULTS
[18:44:21] ======================================================================
[18:44:21] wave4-trial-0009 0/7 full mean 28s / 5.1r ❌ CRASHES
[18:44:21] exp13-gentrack-v4 0/7 full mean 28s / 4.6r ❌ CRASHES
[18:44:21] wave5-gentrack-only 0/7 full mean 28s / 4.8r ❌ CRASHES