ResearchBenchmarksImitation Learning on PendulumFollow-179.6Mean ScoreExpert (TRPO)-673.496-545.273-417.05-288.827Oct 30, 2017Evaluation ResultsMethodMethodLinksMean ScoreExpert (TRPO)2017.10-179.6AIRLstate-only=falsestate-only=false2017.10-204.7AIRLstate-only=truestate-only=true2017.10-221.5GAIL2017.10-226GAN-GCL2017.10-261.5Random2017.10-654.5