paulh
/
donkeycar-rl-autoresearch
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

docs: TEST_HISTORY Exp10 plan added 

Exp10: generated_track + mountain_track, v5 reward, throttle_min=0.2
Same as Exp9 but with visual diversity from second track.

Agent: pi
This commit is contained in:
Paul Huliganga 2026-04-18 17:59:07 -04:00
parent b19dcc8b80
commit fecba1dd35
1 changed files with 15 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
docs/TEST_HISTORY.md
View File

@ -225,3 +225,18 @@ Train on mountain_track + generated_track together (v5 reward, throttle_min=0.2)
Both tracks have random lighting each episode → model forced to learn lighting-invariant features. Both tracks have random lighting each episode → model forced to learn lighting-invariant features.
Goal: model that is reliable on both training tracks, then test generalisation to generated_road and mini_monaco. Goal: model that is reliable on both training tracks, then test generalisation to generated_road and mini_monaco.
### Exp 10 — Two tracks: generated_track + mountain_track, v5 reward, throttle_min=0.2
- **Change from Exp9:** Added generated_track as second training track
- **Reward:** v5 (speed × CTE) — unchanged
- **throttle_min:** 0.2 — unchanged from Exp9
- **Training tracks:** generated_track + mountain_track (round-robin, switch every 6,000 steps)
- **Total steps:** 90,000 | Steps per switch: 6,000 | ~7.5 rotations through both tracks
- **lr:** 0.000725 — unchanged
- **Hypothesis:** Adding generated_track visual diversity forces model to learn
lighting-invariant road-following features. Mountain_track teaches hill throttle.
Together should generalise better to generated_road and potentially mini_monaco.
- **Expected results:** mountain_track reliable, generated_track reliable,
generated_road improved, mini_monaco TBD
- **This is essentially Trial 9 repeated with:** v5 reward + throttle_min=0.2 + proper checkpointing + exploit fix