List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on Ant kinematic shifts

120ScoreDROCO
84.74493.897103.05112.203Dec 2, 2025
Updated 8mo ago

Evaluation results

MethodLinks
DROCOSource Policy=expert, Target Policy=expert2025.12120
IGDFSource Policy=expert, Target Policy=expert2025.12119.2
IGDFSource Policy=medium, Target Policy=expert2025.12112.4
OTDFSource Policy=expert, Target Policy=expert2025.12111.6
IQLSource Policy=expert, Target Policy=expert2025.12111
DROCOSource Policy=medium, Target Policy=expert2025.12110.3
IQLSource Policy=medium, Target Policy=expert2025.12107.6
OTDFSource Policy=medium, Target Policy=expert2025.12105.9
DROCOSource Policy=expert, Target Policy=medium2025.12100.4
OTDFSource Policy=expert, Target Policy=medium2025.1298.6
IQLSource Policy=expert, Target Policy=medium2025.1293.7
DROCOSource Policy=medium, Target Policy=medium2025.1292.7
IGDFSource Policy=expert, Target Policy=medium2025.1290.2
IQLSource Policy=medium, Target Policy=medium2025.1289.9
IGDFSource Policy=medium, Target Policy=medium2025.1288
OTDFSource Policy=medium, Target Policy=medium2025.1286.1