donkeycar-rl-autoresearch/docs
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
..
track-screenshots wave3: add multi-track autoresearch system (83 tests passing) 2026-04-14 12:47:12 -04:00
ARCHITECTURE.md docs: ARCHITECTURE.md — complete system architecture guide 2026-04-17 14:06:38 -04:00
RESEARCH_LOG.md wave3: add multi-track autoresearch system (83 tests passing) 2026-04-14 12:47:12 -04:00
SESSION_LOG_2026-04-19.md docs: Exp 11 + 11b results — parallel envs work, v6 prevents circles, but plateaus at ~194 steps 2026-04-19 13:26:29 -04:00
STATE.md docs: STATE.md updated with April 16 test results 2026-04-16 20:45:45 -04:00
TEST_HISTORY.md docs: Exp 11 + 11b results — parallel envs work, v6 prevents circles, but plateaus at ~194 steps 2026-04-19 13:26:29 -04:00