ResearchBenchmarksReinforcement Learning on Flappy Task 5Follow9.55Grand Average Return (G)Qreg+NWLU2.40524.26016.1157.9699May 21, 2026Evaluation ResultsMethodMethodLinksGrand Average Return (G)Qreg+NWLU2026.059.55Qreg2026.058.83PM2026.057.29PackNet2026.055.15MER2026.054.86DQN2026.054.69DDQN2026.054.47EWC2026.053.3L22026.052.68