ResearchBenchmarksLocomotion on Ant v2Follow10,133Average ReturnTD74,394.285,884.147,3748,863.86May 24, 2024Evaluation ResultsMethodMethodLinksAverage ReturnTD7Time steps=5MTime steps=5M2024.0510,133TD3+OFETime steps=5MTime steps=5M2024.058,547RESeLTime steps=5MTime steps=5M2024.058,006TQCTime steps=5MTime steps=5M2024.056,329TD3Time steps=5MTime steps=5M2024.055,589SACTime steps=5MTime steps=5M2024.054,615