List your company

Offline Reinforcement Learning on D4RL MuJoCo (Random, Med-Replay, Medium, Expert Configurations)

1,020.7Total ScoreCABI+TD3_BC
427.9581.8735.7889.6Feb 13, 2022Mar 5, 2022Mar 26, 2022Apr 15, 2022May 6, 2022May 26, 2022Jun 16, 2022

Evaluation results

MethodLinks
CABI+TD3_BC2022.061,020.715.111.96.444.431.329.445.1100.482105112.7108.4107.6112.4108.6
TD3_BC2022.06979.310.2111.443.331.425.242.899.579.797.9112.2101.1105.7112.2105.7
FisherBRC2022.06974.632.211.40.643.335.642.641.399.479.596.190.6103.6106.8112.379.9
BEAR2022.06802.625.111.47.338.633.719.241.752.159.153.496.340.1108.2110.3106.1
SPOT2022.02773———————————————
CQL2022.06764.321.710.72.741.928.615.837.244.257.527.1111.4—82.4111.2103.8
CQL2022.02698.5———————————————
IQL2022.02692.4———————————————
Onestep2022.02684.6———————————————
TD3+BC2022.02677.4———————————————
DT2022.02672.6———————————————
UWAC2022.06618.62.39.83.838.9188.437.430.317.440.695.414.8104109.188.4
BC2022.06595.329.51.234.719.78.336.63011.467.689.612105.2111.556
BC2022.02466.7———————————————
AWAC2022.02450.7———————————————
BCQ2022.06—2.210.64.938.233.11540.754.553.164.7110.957.5———
MOPO2022.06—35.411.713.653.167.53942.32817.863.323.744.6———