ResearchBenchmarksReinforcement Learning on Flappy Task 4Follow18.01Grand Average ReturnQreg+NWLU4.94768.338811.7315.1212May 21, 2026Evaluation ResultsMethodMethodLinksGrand Average ReturnQreg+NWLU2026.0518.01Qreg2026.0517.69PM2026.0514.29PackNet2026.0511.75DQN2026.0511.12MER2026.0510.99DDQN2026.0510.41EWC2026.057.22L22026.055.45