List your company

Locomotion on D4RL HalfCheetah-medium-replay v2

91.65Online Normalized ReturnROID
38.3552.187566.02579.8625May 28, 2026May 29, 2026

Evaluation results

MethodLinks
ROIDseeds=3, evaluation_rollouts=10, step_interval=50002026.0591.6543.9
BOORLevaluation_rollouts=10, step_interval=50002026.0591.544.5
RLPDevaluation_rollouts=10, step_interval=50002026.0587.6—
Cal-QLevaluation_rollouts=10, step_interval=50002026.0559.546.5
PEXevaluation_rollouts=10, step_interval=50002026.0555.244.1
DUALTime steps=1M, Number of random seeds=52026.0548.78—
DACERTime steps=1M, Number of random seeds=52026.0548.18—
Diff-QLTime steps=1M, Number of random seeds=52026.0546.91—
EDISTime steps=1M, Number of random seeds=52026.0546.65—
DiffuserTime steps=1M, Number of random seeds=52026.0545.82—
IQLTime steps=1M, Number of random seeds=52026.0545.77—
ODTevaluation_rollouts=10, step_interval=50002026.0540.439.9