ResearchBenchmarksLocomotion Control on D4RL walker2d randomFollow37.3Normalized ScoreMOREL-1.78.42518.5528.675Feb 16, 2021Dec 31, 2021Nov 15, 2022Sep 30, 2023Aug 14, 2024Jun 29, 2025May 14, 2026Evaluation ResultsMethodMethodLinksNormalized ScoreMOREL2021.0237.3CPQLGradient steps=1MGradient steps=1M2026.0521.2EDACGradient steps=3MGradient steps=3M2026.0516.6MOPO2021.0213.6BC2021.029.8PBRLGradient steps=1MGradient steps=1M2026.058.1BEAR2021.027.3COMBO2021.027CQL2021.027SAC-off2021.024.1UWACGradient steps=1MGradient steps=1M2026.052BRAC-v2021.021.9BRAC-p2021.02-0.2