List your company

Control Task on OpenAI Gym CarRacing

-6.3987T-statisticPOEM
-6.718635-6.558668-6.3987-6.238732Jan 21, 2026

Evaluation results

MethodLinks
POEMtraining timesteps=500,000, experiments=10, evaluation episodes=15, baseline=PPO2026.01-6.39870.0002—