List your company

Offline Control on Heterogeneous Pendulum 300,000 transition steps (Mid-Data)

-1.25Cumulative RewardAOC
-718.0596-531.9648-345.87-159.7752Oct 11, 2023

Evaluation results

MethodLinks
AOC2023.10-1.25
MPC2023.10-1.34
MFRL2023.10-11.95
BC2023.10-225.32
Data-Avg-Return2023.10-245.54
KNN2023.10-670.51
1NN2023.10-690.49