donkeycar-rl-autoresearch/agent/models/exp22-generated-pair-warm-v6
Paul Huliganga c5c4ca658e chore(exp22): update wedgefix run log — training stopped for strategy rethink
Run stopped at ~34k steps. ep_len_mean frozen at 118 due to MAX_EPISODE_SECONDS=18
cap. Barriers identified as zero-thickness MeshColliders (physics tunneling root cause).
Clean-slate rebuild planned: BoxCollider barriers + CCD on car + simplified reward.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-05 15:36:18 -04:00
..
current.pid feat(exp22): add solid-hit/wedge/high-CTE exploit fixes and generated-pair warm experiments 2026-05-05 14:46:13 -04:00
run_2026-04-28_2132_openfix.log feat(exp22): add solid-hit/wedge/high-CTE exploit fixes and generated-pair warm experiments 2026-05-05 14:46:13 -04:00
run_2026-04-28_211553.log feat(exp22): add solid-hit/wedge/high-CTE exploit fixes and generated-pair warm experiments 2026-05-05 14:46:13 -04:00
run_2026-04-28_211650.log feat(exp22): add solid-hit/wedge/high-CTE exploit fixes and generated-pair warm experiments 2026-05-05 14:46:13 -04:00
run_2026-05-05_141211_barrierfix.log feat(exp22): add solid-hit/wedge/high-CTE exploit fixes and generated-pair warm experiments 2026-05-05 14:46:13 -04:00
run_2026-05-05_141343_barrierfix.log feat(exp22): add solid-hit/wedge/high-CTE exploit fixes and generated-pair warm experiments 2026-05-05 14:46:13 -04:00
run_2026-05-05_141929_strictcte.log feat(exp22): add solid-hit/wedge/high-CTE exploit fixes and generated-pair warm experiments 2026-05-05 14:46:13 -04:00
run_2026-05-05_142620_wedgefix.log chore(exp22): update wedgefix run log — training stopped for strategy rethink 2026-05-05 15:36:18 -04:00
run_2026-05-05_restart.log feat(exp22): add solid-hit/wedge/high-CTE exploit fixes and generated-pair warm experiments 2026-05-05 14:46:13 -04:00
run_session.log feat(exp22): add solid-hit/wedge/high-CTE exploit fixes and generated-pair warm experiments 2026-05-05 14:46:13 -04:00