List your company

Single-agent Reinforcement Learning (SARL) on Pong Clean

18.5Average Episode ReturnBehaviorGuard
2.7966.87310.9515.027May 7, 2026

Evaluation results

MethodLinks
BehaviorGuard2026.0518.5
SHINE2026.0518.2
Original2026.0516.9
STRIP2026.0515.2
FeatureRE2026.057.3
Direct retraining2026.057.1
NC2026.053.4