List your company

Offline Imitation Learning on D4RL MuJoCo reward-free v2 (medium, medium-replay, medium-expert)

110.4Hopper-v2 (m) ScoreCEIL
17.73641.79365.8589.907Jun 26, 2023

Evaluation results

MethodLinks
CEIL2023.06110.4103106.84030.363.9118.6110.8117126.3122114.31,163.5
ValueDICE2023.0673.883.650.81.92.43.224.626.444.179.182.475.2547.5
SMODICE2023.0656.128.76842.737.766.966.240.758.287.469.9113.4735.9
DemoDICE2023.0654.832.765.442.83755.668.139.79585.669108.8754.6
ORILBackbone=TD3+BC2023.0650.922.172.744.730.287.547.126.7102.646.531.461.9624.3
SQILBackbone=TD3+BC2023.0632.660.625.513.225.314.425.615.6863.658.444.3387.1
IQ-Learn2023.0621.319.924.957.57.522.319.618.538.424.355.3264.5