paulh
/
donkeycar-rl-autoresearch
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Research-grade DonkeyCar RL autoresearch and sweep system.
67 Commits 1 Branch 0 Tags 207 MiB
Python 94.3%
Shell 5.7%
Go to file
Paul Huliganga 47d8e5b346 fix: short-lap exploit now TERMINATES the episode, not just penalises 
The circle exploit persisted because the penalty alone (-100 per short
lap) was insufficient. The model stayed alive between laps accumulating
small positive rewards, making circling a viable strategy despite the
penalty.

Fix: _compute_reward_and_done() returns (reward, force_terminate).
When a short lap is detected, force_terminate=True is returned and
step() sets terminated=True immediately. The episode ends on the spot —
no more rewards possible. This makes the circle exploit strictly worse
than any forward driving behaviour.

Tests updated: _compute_reward → _compute_reward_and_done, short-lap
test now asserts force_terminate=True.

Agent: pi
Tests: 102 passed
Tests-Added: 0
TypeScript: N/A
 		2026-04-18 10:42:23 -04:00
.harness feat: Wave 1 complete — real PPO training, model save, GP+UCB autoresearch, 37 tests passing 2026-04-13 10:03:15 -04:00
agent fix: short-lap exploit now TERMINATES the episode, not just penalises 2026-04-18 10:42:23 -04:00
docs docs: ARCHITECTURE.md — complete system architecture guide 2026-04-17 14:06:38 -04:00
tests fix: short-lap exploit now TERMINATES the episode, not just penalises 2026-04-18 10:42:23 -04:00
.gitignore feat: Wave 1 complete — real PPO training, model save, GP+UCB autoresearch, 37 tests passing 2026-04-13 10:03:15 -04:00
AGENT.md feat: Wave 1 complete — real PPO training, model save, GP+UCB autoresearch, 37 tests passing 2026-04-13 10:03:15 -04:00
DECISIONS.md docs: ADR-017 — always save best model, never just latest 2026-04-17 16:03:59 -04:00
IMPLEMENTATION_PLAN.md feat: Phase 3 — behavioral control, enhanced evaluator, 53 tests 2026-04-14 09:28:43 -04:00
PROJECT-KICKOFF.md feat: Wave 1 complete — real PPO training, model save, GP+UCB autoresearch, 37 tests passing 2026-04-13 10:03:15 -04:00
PROJECT-SPEC.md feat: Wave 1 complete — real PPO training, model save, GP+UCB autoresearch, 37 tests passing 2026-04-13 10:03:15 -04:00
README.md feat: Wave 1 complete — real PPO training, model save, GP+UCB autoresearch, 37 tests passing 2026-04-13 10:03:15 -04:00
create_gitea_repo.py Initial commit 2026-04-12 23:44:36 -04:00
ralph-loop.sh feat: Wave 1 complete — real PPO training, model save, GP+UCB autoresearch, 37 tests passing 2026-04-13 10:03:15 -04:00

README.md

donkeycar-rl-autoresearch

Purpose

Status

  • Scaffolded with the agent harness
  • Spec not filled yet

Runbook

  • Fill PROJECT-SPEC.md
  • Create IMPLEMENTATION_PLAN.md from the spec
  • Start the implementation loop