List your company

Offline Reinforcement Learning on MujoCo halfcheetah

62.86Normalized ReturnCEDGE-Policy
-6.050411.839829.7347.6202Dec 8, 2025Jan 4, 2026Feb 1, 2026Mar 1, 2026Mar 29, 2026Apr 26, 2026May 24, 2026

Evaluation results

MethodLinks
CEDGE-PolicyType=kin-thighjnt, Level=M2026.0562.86
DiffuserType=kin-thighjnt, Level=M2026.0561.98
CEDGE-PlannerType=kin-thighjnt, Level=M2026.0561.41
Real DatasetOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=no-DP2025.1260.8
MOBODYType=kin-thighjnt, Level=M2026.0559.17
CEDGE-PolicyType=kin-thighjnt, Level=H2026.0558.43
MOBODYType=kin-thighjnt, Level=H2026.0556.72
PrivORL-nOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=102025.1248.8
Real DatasetOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=no-DP2025.1248.5
Real DatasetOffline RL Algorithm=IQL, Privacy Budget (epsilon)=no-DP2025.1248.3
CEDGE-PlannerType=kin-thighjnt, Level=H2026.0548.27
PrivORL-nOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=102025.1245.2
CEDGE-PolicyType=kin-footjnt, Level=M2026.0542.14
TD3-BCType=kin-thighjnt, Level=M2026.0541.77
IQLType=kin-thighjnt, Level=M2026.0541.27
MOBODYType=morph-torso, Level=H2026.0540.45
CEDGE-PolicyType=morph-torso, Level=H2026.0539.98
PrivORL-nOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=12025.1238.7
PrivORL-nOffline RL Algorithm=IQL, Privacy Budget (epsilon)=102025.1236.9
BOSAType=kin-footjnt, Level=M2026.0536.79
DiffuserType=morph-torso, Level=H2026.0536.18
IQLType=kin-footjnt, Level=M2026.0534.71
DiffuserType=kin-thighjnt, Level=H2026.0534.49
DARAType=kin-footjnt, Level=M2026.0533.48
CEDGE-PlannerType=morph-torso, Level=H2026.0533.08
MOBODYType=kin-footjnt, Level=M2026.0531.88
BOSAType=kin-thighjnt, Level=H2026.0531.72
IQLType=kin-footjnt, Level=H2026.0531.68
IQLType=kin-thighjnt, Level=H2026.0531.6
DARAType=kin-thighjnt, Level=H2026.0531.46
DARAType=kin-footjnt, Level=H2026.0531.19
TD3-BCType=kin-thighjnt, Level=H2026.0531.1
TD3-BCType=kin-footjnt, Level=M2026.0530.19
CEDGE-PlannerType=kin-footjnt, Level=M2026.0529.85
DARAType=morph-torso, Level=H2026.0529.41
CEDGE-PlannerType=morph-thigh, Level=H2026.0529.37
CEDGE-PolicyType=morph-thigh, Level=M2026.0528.91
MOBODYType=morph-thigh, Level=H2026.0528.51
DiffuserType=morph-thigh, Level=H2026.0528.31
IQLType=morph-torso, Level=H2026.0527.81
PrivORL-nOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=12025.1227.4
MOBODYType=morph-thigh, Level=M2026.0527.18
CEDGE-PlannerType=kin-footjnt, Level=H2026.0527.08
CEDGE-PolicyType=morph-torso, Level=M2026.0526.54
CEDGE-PolicyType=morph-thigh, Level=H2026.0526.19
PrivORL-nOffline RL Algorithm=IQL, Privacy Budget (epsilon)=12025.1225.2
MOBODYType=morph-torso, Level=M2026.0523.92
BOSAType=morph-thigh, Level=M2026.0522.83
DiffuserType=kin-footjnt, Level=M2026.0522.53
TD3-BCType=morph-thigh, Level=H2026.0522.19
IQLType=morph-thigh, Level=H2026.0521.69
BOSAType=morph-thigh, Level=H2026.0520.77
IQLType=morph-thigh, Level=M2026.0520.49
TD3-BCType=morph-thigh, Level=M2026.0519.49
MOBODYType=kin-footjnt, Level=H2026.0518.51
DiffuserType=morph-torso, Level=M2026.0517.49
BOSAType=morph-torso, Level=H2026.0517.09
DARAType=kin-thighjnt, Level=M2026.0515.47
CEDGE-PlannerType=morph-torso, Level=M2026.0515.34
BOSAType=kin-thighjnt, Level=M2026.0514.92
BOSAType=kin-footjnt, Level=H2026.0514.7
DiffuserType=kin-footjnt, Level=H2026.0514.69
TD3-BCType=kin-footjnt, Level=H2026.0514.05
CEDGE-PolicyType=kin-footjnt, Level=H2026.0512.97
CEDGE-PlannerType=morph-thigh, Level=M2026.0512.31
DiffuserType=morph-thigh, Level=M2026.0512.22
DARAType=morph-thigh, Level=M2026.0510.9
DARAType=morph-thigh, Level=H2026.0510.35
TD3-BCType=morph-torso, Level=M2026.055.86
PrePATE-GANOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=102025.125.6
PrePATE-GANOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=12025.125.3
PGMOffline RL Algorithm=IQL, Privacy Budget (epsilon)=102025.124.5
PATE-GANOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=12025.124
PrePATE-GANOffline RL Algorithm=IQL, Privacy Budget (epsilon)=102025.123.6
PrePATE-GANOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=12025.123
PrePATE-GANOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=102025.123
DARAType=morph-torso, Level=M2026.052.91
TD3-BCType=morph-torso, Level=H2026.052.73
PATE-GANOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=102025.122.5
PrivSynOffline RL Algorithm=IQL, Privacy Budget (epsilon)=102025.122.4
IQLType=morph-torso, Level=M2026.051.87
PATE-GANOffline RL Algorithm=IQL, Privacy Budget (epsilon)=12025.121.8
PrePATE-GANOffline RL Algorithm=IQL, Privacy Budget (epsilon)=12025.121.8
PATE-GANOffline RL Algorithm=IQL, Privacy Budget (epsilon)=102025.121.7
BOSAType=morph-torso, Level=M2026.051.67
PGMOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=102025.121.6
PGMOffline RL Algorithm=IQL, Privacy Budget (epsilon)=12025.121.5
PrivSynOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=102025.121.3
PrivSynOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=12025.120.4
PGMOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=102025.120.2
PGMOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=12025.120
PGMOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=12025.120
PrivSynOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=12025.120
PrivSynOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=102025.120
PrivSynOffline RL Algorithm=IQL, Privacy Budget (epsilon)=12025.120
PATE-GANOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=12025.12-2.8
PATE-GANOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=102025.12-3.4