donkeycar-rl-autoresearch/agent/models
Paul Huliganga 138c65270f feat(exp22): add solid-hit/wedge/high-CTE exploit fixes and generated-pair warm experiments
- reward_wrapper: detect barrier/wall/tree solid hits, terminate on head-on impact
  or 4 sustained solid-hit frames; prevents car wedging against invisible barriers
- reward_wrapper: add low-speed/wedge termination — kills episode when car is pinned
  motionless (below threshold, no displacement) after grace period
- reward_wrapper: high-CTE exploit fix — return -0.25 immediately when CTE >
  max_cte_terminate (not after patience), so PPO cannot collect positive speed
  rewards while driving the large outside-road circle
- tests: 23 passing unit tests covering all new termination paths
- exp20/21/22: add parallel DummyVecEnv experiments on generated_road+generated_track
  with warm-start from champion model; exp22 is current active run
- SESSION_HANDOFF.md: live handoff doc for next session continuity

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-05 14:46:13 -04:00
..
ARCHIVED_reward_hacking/champion_hacked fix: hack-proof reward shaping + reward hacking detection + research log 2026-04-13 12:27:48 -04:00
champion feat: Phase 3 — behavioral control, enhanced evaluator, 53 tests 2026-04-14 09:28:43 -04:00
exp14-mountain-v5-finetune docs: capture robust mountain finetune winner at 36k and preserve eval comparison 2026-04-20 00:43:27 -04:00
exp20-parallel-450k-v5 feat(exp22): add solid-hit/wedge/high-CTE exploit fixes and generated-pair warm experiments 2026-05-05 14:46:13 -04:00
exp20-parallel-450k-v5_pre-fix_2026-04-28_163923 feat(exp22): add solid-hit/wedge/high-CTE exploit fixes and generated-pair warm experiments 2026-05-05 14:46:13 -04:00
exp21-generated-pair-warm-v4 feat(exp22): add solid-hit/wedge/high-CTE exploit fixes and generated-pair warm experiments 2026-05-05 14:46:13 -04:00
exp22-generated-pair-warm-v6 feat(exp22): add solid-hit/wedge/high-CTE exploit fixes and generated-pair warm experiments 2026-05-05 14:46:13 -04:00
wave3-champion wave3: autoresearch trial 5 results 2026-04-14 18:22:44 -04:00
wave4-champion wave3: autoresearch trial 5 results 2026-04-15 07:15:57 -04:00