ResearchBenchmarksImitation Learning from Observation on Swimmer v4Follow0.73AERRandom-13.68880483.638123180.96505278.291977Jan 24, 2026Evaluation ResultsMethodMethodLinksAERPerformance ScoreRandomseeds=10,000seeds=10,0002026.010.73—MAHALOseeds=10,000seeds=10,0002026.0187.41720.0248BCOseeds=10,000seeds=10,0002026.01347.18420.9768OPOLOseeds=10,000seeds=10,0002026.01352.24560.991Teacherseeds=10,000seeds=10,0002026.01355.4238—CILOseeds=10,000seeds=10,0002026.01356.86931.0041GAIfOseeds=10,000seeds=10,0002026.01360.54951.0145UfOseeds=10,000seeds=10,0002026.01361.20011.0163