[21:15:19] ======================================================================
[21:15:19] Eval: generated-track specialists on mini-monaco (zero-shot)
[21:15:19] Track   : donkey-minimonaco-track-v0
[21:15:19] Episodes: 7 x max 2000 steps
[21:15:19] Host    : localhost:9091
[21:15:19] Log     : /home/paulh/projects/donkeycar-rl-autoresearch/agent/models/eval_gentrack_minimonaco_20260506_211519.log
[21:15:19] ======================================================================
[21:15:19] 
[21:15:19] ── exp13-gentrack-v4 ──────────────────────────────────────
[21:15:19]    Model: /home/paulh/projects/donkeycar-rl-autoresearch/agent/models/exp13-gentrack-v4/best_model.zip
[21:15:48]    ep1: 5.7r / 2000s  ✅
[21:16:15]    ep2: 5.8r / 2000s  ✅
[21:16:41]    ep3: 5.6r / 2000s  ✅
[21:17:08]    ep4: 5.8r / 2000s  ✅
[21:17:34]    ep5: 5.7r / 2000s  ✅
[21:18:01]    ep6: 5.8r / 2000s  ✅
[21:18:27]    ep7: 5.7r / 2000s  ✅
[21:18:27]    SUMMARY: 7/7 full  |  mean 2000s / 5.7r  |  ✅ DRIVES
[21:18:29] 
[21:18:29] ── wave5-gentrack-only ──────────────────────────────────────
[21:18:29]    Model: /home/paulh/projects/donkeycar-rl-autoresearch/agent/models/wave5-gentrack-only/model.zip
[21:18:57]    ep1: 5.7r / 2000s  ✅
[21:19:23]    ep2: 5.9r / 2000s  ✅
[21:19:50]    ep3: 5.8r / 2000s  ✅
[21:20:16]    ep4: 5.8r / 2000s  ✅
[21:20:43]    ep5: 5.9r / 2000s  ✅
[21:21:09]    ep6: 5.6r / 2000s  ✅
[21:21:36]    ep7: 5.7r / 2000s  ✅
[21:21:36]    SUMMARY: 7/7 full  |  mean 2000s / 5.8r  |  ✅ DRIVES
[21:21:38] 
[21:21:38] ── wave4-trial-0009 ──────────────────────────────────────
[21:21:38]    Model: /home/paulh/projects/donkeycar-rl-autoresearch/agent/models/wave4-trial-0009/model.zip
[21:21:52]    ep1: 5.3r / 859s  ❌@859
[21:22:06]    ep2: 5.3r / 847s  ❌@847
[21:22:19]    ep3: 4.9r / 850s  ❌@850
[21:22:33]    ep4: 5.0r / 904s  ❌@904
[21:23:00]    ep5: 6.3r / 2000s  ✅
[21:23:27]    ep6: 6.0r / 2000s  ✅
[21:23:40]    ep7: 4.9r / 857s  ❌@857
[21:23:41]    SUMMARY: 2/7 full  |  mean 1188s / 5.4r  |  ✅ DRIVES
[21:23:43] 
[21:23:43] ======================================================================
[21:23:43] FINAL RESULTS
[21:23:43] ======================================================================
[21:23:43]   exp13-gentrack-v4          7/7 full  mean   2000s /     5.7r  ✅ DRIVES
[21:23:43]   wave5-gentrack-only        7/7 full  mean   2000s /     5.8r  ✅ DRIVES
[21:23:43]   wave4-trial-0009           2/7 full  mean   1188s /     5.4r  ✅ DRIVES
[21:23:43] 
Log saved: /home/paulh/projects/donkeycar-rl-autoresearch/agent/models/eval_gentrack_minimonaco_20260506_211519.log