ResearchBenchmarksWalker-stand on DeepMind Control Suite (Total Average Return)Walker-stand on DeepMind Control Suite (Total Average Return)Follow997Total ReturnQSM208.68413.34618822.66Jun 29, 2026Evaluation resultsMethodMethodLinksTotal ReturnQSM2026.06997BRO2026.06995BRO-Fast2026.06995SAC2026.06991Dual-Flow RL2026.06990TD32026.06990FlowRL2026.06985DDPG2026.06985D4PG2026.06983MPO2026.06977QVPO2026.06974TRPO2026.06302A2C2026.06239