ResearchBenchmarksLocomotion on Antmaze l-play v2Follow93D4RL Score (%)Inverter50.56861.58472.683.616May 22, 2026Evaluation ResultsMethodMethodLinksD4RL Score (%)Time per Env Step (ms)InverterEpisodes=100, Seeds=4,...Episodes=100, Seeds=4, Hardware=single A40 GPU, Framework=PyTorch, Batch size=1, Cuda-synced=true2026.05930.13ReBRACEpisodes=100, Seeds=4Episodes=100, Seeds=42026.0552.2—BC-10%Hardware=single A40 GP...Hardware=single A40 GPU, Framework=PyTorch, Batch size=1, Cuda-synced=true2026.05—1.25