List your company

Control Task on Lunar Lander (test)

255.57Average RewardPPO
-241.0924-112.151216.79145.7312Mar 15, 2025May 8, 2025Jul 2, 2025Aug 25, 2025Oct 19, 2025Dec 12, 2025Feb 5, 2026

Evaluation results

MethodLinks
PPOVRER=true2026.02255.57—
PPOVRER=false2026.02224.43—
TRPOVRER=true2026.02184.16—
TRPOVRER=false2026.02139.17—
DPWSimulations=10002025.0363.20.008
AG-DPWSimulations=10002025.0361.280.203
VPWSimulations=10002025.0360.940.009
AG-VPWSimulations=10002025.0360.280.216
DPWSimulations=5622025.0359.80.005
AG-DPWSimulations=5622025.0359.310.046
VPWSimulations=5622025.0358.450.005
AG-VPWSimulations=5622025.0357.560.059
DPWSimulations=3162025.0355.80.008
AG-VPWSimulations=3162025.0354.490.017
VPWSimulations=3162025.0354.460.007
AG-DPWSimulations=3162025.03540.239
AG-DPWSimulations=1782025.0350.690.004
DPWSimulations=1782025.0350.240.002
AG-VPWSimulations=1782025.0348.790.203
VPWSimulations=1782025.0347.460.002
AG-VPWSimulations=1002025.0344.630.086
DPWSimulations=1002025.0344.40.019
AG-DPWSimulations=1002025.0344.220.022
VPWSimulations=1002025.0339.230.083
PPO2025.080.846—
MLES2025.080.819—
EoH2025.080.776—
Initial policy2025.080.653—
DQN2025.080.508—
A2CVRER=true2026.02-186.53—
A2CVRER=false2026.02-221.99—