Commit Graph

2 Commits

Author SHA1 Message Date
Paul Huliganga 0993d4f1e7 docs: Exp 11 + 11b results — parallel envs work, v6 prevents circles, but plateaus at ~194 steps
Exp 11 (v5 reward): aborted at 66k — circular driving returned without efficiency term
Exp 11b (v6 reward): completed 90k — no circles but plateaus at 170-195 steps
All 4 tracks eval: remarkably consistent ~194 steps (including zero-shot)
Parallel DummyVecEnv infrastructure proven stable.
Next: increase training budget (90k may be insufficient for 2 parallel envs).
2026-04-19 13:26:29 -04:00
Paul Huliganga 86357622e3 docs: session log + ADR-019 — parallel DummyVecEnv for multi-track training 2026-04-19 10:50:11 -04:00