List your company

Offline Reinforcement Learning under Gravity Shift on MuJoCo HalfCheetah

83.05Normalized ReturnMOBODY
-0.09821.488543.07564.6615May 13, 2026May 14, 2026May 16, 2026May 18, 2026May 20, 2026May 22, 2026May 24, 2026

Evaluation results

MethodLinks
MOBODYLevel=5.02026.0583.05
CEDGE-PolicyLevel=5.02026.0575.34
TD3-BCLevel=5.02026.0573.75
CEDGE-PlannerLevel=0.52026.0549.84
DiffuserLevel=0.52026.0548.45
MOBODYLevel=0.52026.0547.18
DARALevel=0.52026.0546.11
DARASource Data=half-m-e, Target Data=e2026.0545.3
IQLLevel=0.52026.0544.23
IQLLevel=5.02026.0544
BOSALevel=0.52026.0543.96
IQL*Source Data=half-m-e, Target Data=e2026.0543.4
SRPOSource Data=half-m-e, Target Data=m-e2026.0543.3
SRPOSource Data=half-m-e, Target Data=e2026.0543.3
SRPOSource Data=half-m-e, Target Data=m2026.0542.5
IQL*Source Data=half-m, Target Data=e2026.0542.4
BOSASource Data=half-m-e, Target Data=m2026.0541.8
TCE(SM)Source Data=half-m-e, Target Data=e2026.0541.7
CEDGE-PolicyLevel=2.02026.0541.66
MOBODYLevel=2.02026.0541.6
TCE(SM)Source Data=half-m-e, Target Data=m-e2026.0541.3
DARASource Data=half-m, Target Data=m2026.0541.2
TCE(SM)Source Data=half-m, Target Data=e2026.0541.1
IGDFSource Data=half-m-e, Target Data=e2026.0541.1
OTDFSource Data=half-m, Target Data=m2026.0540.7
TCE(SM)Source Data=half-m, Target Data=m2026.0540.7
DARASource Data=half-m, Target Data=m-e2026.0540.7
SRPOSource Data=half-m, Target Data=m-e2026.0540.7
IGDFSource Data=half-m-e, Target Data=m-e2026.0540.7
BOSASource Data=half-m, Target Data=e2026.0540.5
BOSASource Data=half-m, Target Data=m-e2026.0540.4
BOSASource Data=half-m-e, Target Data=e2026.0539.9
DARASource Data=half-m, Target Data=e2026.0539.8
IQL*Source Data=half-m, Target Data=m2026.0539.6
IQL*Source Data=half-m, Target Data=m-e2026.0539.6
IGDFSource Data=half-m, Target Data=e2026.0539.6
IQL*Source Data=half-m-e, Target Data=m-e2026.0539.6
OTDFSource Data=half-m-e, Target Data=m2026.0539.5
SRPOSource Data=half-m, Target Data=e2026.0539.4
TCE(SM)Source Data=half-m-e, Target Data=m2026.0539.4
DARASource Data=half-m-e, Target Data=m-e2026.0539.4
TCE(SM)Source Data=half-m, Target Data=m-e2026.0539.2
BOSASource Data=half-m, Target Data=m2026.0538.9
IGDFSource Data=half-m, Target Data=m-e2026.0538.7
BOSASource Data=half-m-e, Target Data=m-e2026.0538.7
IQL*Source Data=half-m-e, Target Data=m2026.0538.6
DARASource Data=half-m-e, Target Data=m2026.0537.8
IGDFSource Data=half-m-e, Target Data=m2026.0537.7
SRPOSource Data=half-m, Target Data=m2026.0536.9
IGDFSource Data=half-m, Target Data=m2026.0536.6
OTDFSource Data=half-m, Target Data=e2026.0536.1
OTDFSource Data=half-m-e, Target Data=m-e2026.0532.4
DARALevel=2.02026.0531.85
IQLLevel=2.02026.0531.34
TD3-BCLevel=2.02026.0529.29
OTDFSource Data=half-m, Target Data=m-e2026.0528.6
BOSALevel=2.02026.0527.86
DARALevel=5.02026.0527.67
DiffuserLevel=2.02026.0527.38
CEDGE-PlannerLevel=2.02026.0527.19
OTDFSource Data=half-m-e, Target Data=e2026.0526.5
SRPOSource Data=half-m-r, Target Data=e2026.0523.1
DARASource Data=half-m-r, Target Data=e2026.0522.4
OTDFSource Data=half-m-r, Target Data=m2026.0521.5
IQL*Source Data=half-m-r, Target Data=e2026.0520.7
DiffuserLevel=5.02026.0520.33
TCE(SM)Source Data=half-m-r, Target Data=m-e2026.0520.3
DARASource Data=half-m-r, Target Data=m-e2026.0520.2
IQL*Source Data=half-m-r, Target Data=m2026.0520.1
CEDGE-PolicyLevel=0.12026.0520.04
BOSASource Data=half-m-r, Target Data=m2026.0520
TCE(SM)Source Data=half-m-r, Target Data=m2026.0518.1
BOSALevel=5.02026.0517.95
DARASource Data=half-m-r, Target Data=m2026.0517.6
SRPOSource Data=half-m-r, Target Data=m2026.0517.5
IQL*Source Data=half-m-r, Target Data=m-e2026.0517.2
BOSASource Data=half-m-r, Target Data=m-e2026.0516.7
SRPOSource Data=half-m-r, Target Data=m-e2026.0516.3
TCE(SM)Source Data=half-m-r, Target Data=e2026.0515.5
BOSASource Data=half-m-r, Target Data=e2026.0515.4
IGDFSource Data=half-m-r, Target Data=e2026.0515.3
TCE(OG)Source Data=half-m, Target Data=e2026.0514.8
OTDFSource Data=half-m-r, Target Data=m-e2026.0514.7
IGDFSource Data=half-m-r, Target Data=m2026.0514.4
MOBODYLevel=0.12026.0514.18
DARALevel=0.12026.0512.9
OTDFSource Data=half-m-r, Target Data=e2026.0511.4
DiffuserLevel=0.12026.0511.19
CEDGE-PlannerLevel=0.12026.0510.6
IGDFSource Data=half-m-r, Target Data=m-e2026.0510
IQLLevel=0.12026.059.62
BOSALevel=0.12026.059.31
TCE(OG)Source Data=half-m-e, Target Data=e2026.058.5
TCE(OG)Source Data=half-m-r, Target Data=e2026.057.9
TD3-BCLevel=0.12026.056.9
TD3-BCLevel=0.52026.056.38
TCE(OG)Source Data=half-m, Target Data=m2026.054.1
CEDGE-PlannerLevel=5.02026.054.04
TCE(OG)Source Data=half-m-r, Target Data=m2026.054
TCE(OG)Source Data=half-m, Target Data=m-e2026.053.1