List your company

Reinforcement Learning on Pendulum Best

100Normalized ScoreREFLEX
32.71250.18167.6585.119Jun 15, 2026

Evaluation results

MethodLinks
REFLEXPolicy Type=Programmatic & Evolutionary Policies2026.06100
MLESPolicy Type=Programmatic & Evolutionary Policies2026.0684.8
Initial policyPolicy Type=Programmatic & Evolutionary Policies2026.0635.3