List your company

Offline Reinforcement Learning under Gravity Shift on MuJoCo Ant

71.46Normalized ReturnCEDGE-Policy
3.797621.363838.9356.4962May 13, 2026May 14, 2026May 16, 2026May 18, 2026May 20, 2026May 22, 2026May 24, 2026

Evaluation results

MethodLinks
CEDGE-PolicyLevel=5.02026.0571.46
MOBODYLevel=5.02026.0565.45
TCE(OG)Source Data=ant-m-e, Target Data=m2026.0558
TCE(OG)Source Data=ant-m-e, Target Data=e2026.0558
TCE(SM)Source Data=ant-m-r, Target Data=m2026.0557.2
TCE(OG)Source Data=ant-m, Target Data=m2026.0557
TCE(SM)Source Data=ant-m, Target Data=m2026.0556.4
TCE(SM)Source Data=ant-m, Target Data=e2026.0555.7
TCE(OG)Source Data=ant-m, Target Data=e2026.0554.1
TCE(SM)Source Data=ant-m-e, Target Data=m2026.0553.8
TCE(OG)Source Data=ant-m-r, Target Data=m2026.0553.3
TCE(OG)Source Data=ant-m, Target Data=m-e2026.0552.9
TCE(SM)Source Data=ant-m, Target Data=m-e2026.0550.7
TCE(OG)Source Data=ant-m-r, Target Data=e2026.0550.1
TCE(OG)Source Data=ant-m-e, Target Data=m-e2026.0546
MOBODYLevel=2.02026.0545.83
TCE(SM)Source Data=ant-m-e, Target Data=e2026.0545.7
OTDFSource Data=ant-m, Target Data=m2026.0545.1
CEDGE-PolicyLevel=2.02026.0544.42
TCE(SM)Source Data=ant-m-r, Target Data=m-e2026.0544
TCE(SM)Source Data=ant-m-e, Target Data=m-e2026.0543.8
TCE(OG)Source Data=ant-m-r, Target Data=m-e2026.0542.4
BOSALevel=2.02026.0541.77
TCE(SM)Source Data=ant-m-r, Target Data=e2026.0540.5
CEDGE-PolicyLevel=0.12026.0537.99
MOBODYLevel=0.52026.0537.44
IQLLevel=2.02026.0537.17
MOBODYLevel=0.12026.0537.09
DARALevel=2.02026.0536.64
DiffuserLevel=2.02026.0535.84
CEDGE-PolicyLevel=0.52026.0535.16
CEDGE-PlannerLevel=2.02026.0534.11
TD3-BCLevel=2.02026.0534.04
OTDFSource Data=ant-m-e, Target Data=m-e2026.0534
OTDFSource Data=ant-m, Target Data=m-e2026.0533.9
OTDFSource Data=ant-m, Target Data=e2026.0533.2
BOSALevel=5.02026.0531.94
IQLLevel=5.02026.0531.59
DARALevel=5.02026.0531.01
OTDFSource Data=ant-m-r, Target Data=m2026.0529.6
CEDGE-PlannerLevel=5.02026.0527.42
BOSALevel=0.12026.0525.58
OTDFSource Data=ant-m-r, Target Data=m-e2026.0525.4
OTDFSource Data=ant-m-r, Target Data=e2026.0524.5
OTDFSource Data=ant-m-e, Target Data=e2026.0523.2
DARASource Data=ant-m-r, Target Data=m2026.0521.7
IGDFSource Data=ant-m-r, Target Data=m-e2026.0520.3
DARASource Data=ant-m-r, Target Data=e2026.0520
SRPOSource Data=ant-m-r, Target Data=e2026.0519.9
IGDFSource Data=ant-m-r, Target Data=m2026.0519.6
IQL*Source Data=ant-m-r, Target Data=m-e2026.0519.1
BOSALevel=0.52026.0519.03
IQL*Source Data=ant-m-r, Target Data=m2026.0518.9
IGDFSource Data=ant-m-r, Target Data=e2026.0518.8
SRPOSource Data=ant-m-r, Target Data=m2026.0518.7
SRPOSource Data=ant-m-r, Target Data=m-e2026.0518.7
OTDFSource Data=ant-m-e, Target Data=m2026.0518.6
IQL*Source Data=ant-m-r, Target Data=e2026.0518.5
DARASource Data=ant-m-r, Target Data=m-e2026.0518.3
BOSASource Data=ant-m-r, Target Data=m-e2026.0515.9
BOSASource Data=ant-m-r, Target Data=e2026.0514.5
BOSASource Data=ant-m-r, Target Data=m2026.0513.9
TD3-BCLevel=0.12026.0513.23
TD3-BCLevel=0.52026.0512.91
IQLLevel=0.12026.0512.53
DiffuserLevel=0.52026.0512.44
BOSASource Data=ant-m, Target Data=m2026.0512.4
DiffuserLevel=0.12026.0511.92
BOSASource Data=ant-m, Target Data=e2026.0511.8
SRPOSource Data=ant-m, Target Data=m2026.0511.7
BOSASource Data=ant-m, Target Data=m-e2026.0511.6
IGDFSource Data=ant-m, Target Data=m2026.0511.3
CEDGE-PlannerLevel=0.12026.0511.12
DARALevel=0.12026.0511.03
DiffuserLevel=5.02026.0510.46
DARASource Data=ant-m-e, Target Data=e2026.0510.4
IQL*Source Data=ant-m, Target Data=m2026.0510.2
SRPOSource Data=ant-m, Target Data=m-e2026.0510.2
IQL*Source Data=ant-m, Target Data=e2026.0510.2
IQLLevel=0.52026.0510.09
DARASource Data=ant-m, Target Data=m-e2026.0510
DARASource Data=ant-m, Target Data=e2026.059.8
IQL*Source Data=ant-m-e, Target Data=m2026.059.8
IGDFSource Data=ant-m, Target Data=e2026.059.7
SRPOSource Data=ant-m, Target Data=e2026.059.5
DARASource Data=ant-m, Target Data=m2026.059.4
IQL*Source Data=ant-m, Target Data=m-e2026.059.4
IGDFSource Data=ant-m, Target Data=m-e2026.059.4
IGDFSource Data=ant-m-e, Target Data=e2026.059.2
IQL*Source Data=ant-m-e, Target Data=e2026.059.1
DARALevel=0.52026.059.04
IQL*Source Data=ant-m-e, Target Data=m-e2026.059
IGDFSource Data=ant-m-e, Target Data=m2026.058.9
SRPOSource Data=ant-m-e, Target Data=e2026.058.8
SRPOSource Data=ant-m-e, Target Data=m2026.058.4
DARASource Data=ant-m-e, Target Data=m2026.058.1
BOSASource Data=ant-m-e, Target Data=m2026.058.1
IGDFSource Data=ant-m-e, Target Data=m-e2026.057.2
CEDGE-PlannerLevel=0.52026.057.13
DARASource Data=ant-m-e, Target Data=m-e2026.056.4