ResearchBenchmarksFunction Optimization on Ackley 64Follow-0.0036Avg Max RewardGI-PPO-0.663168-0.491934-0.3207-0.149466Dec 14, 2023Evaluation ResultsMethodMethodLinksAvg Max RewardGI-PPO2023.12-0.0036RP2023.12-0.0089LR+RP2023.12-0.0326PPO2023.12-0.1376LR2023.12-0.6378