List your company

Reinforcement Learning on Ant v5

6,633.8Average ReturnQVPO+DBC(*)
-276.9481,517.18853,311.3255,105.4615Dec 4, 2025Dec 20, 2025Jan 5, 2026Jan 22, 2026Feb 7, 2026Feb 23, 2026Mar 12, 2026

Evaluation results

MethodLinks
QVPO+DBC(*)Algorithm=QVPO, Critic=DBC2026.026,633.8
SAC+DBC(*)Algorithm=SAC, Critic=DBC2026.026,501.4
QVPO+CDQAlgorithm=QVPO, Critic=CDQ2026.026,373.2
SAC+TQCAlgorithm=SAC, Critic=TQC2026.026,342.6
SAC+CDQAlgorithm=SAC, Critic=CDQ2026.026,121.8
TD3+DBC(*)Algorithm=TD3, Critic=DBC2026.025,306
SACNoise Variance=02025.124,477.33
TD3+CDQAlgorithm=TD3, Critic=CDQ2026.024,257
SAC - H-EARSAlgorithm Variant=H-EARS, Base Algorithm=SAC2026.034,183
TD3 - H-EARSAlgorithm Variant=H-EARS, Base Algorithm=TD32026.034,125
SACNoise Variance=0.0052025.124,067.61
Full State SACState Dim Removed=None2026.024,000
Full State SACState Dim Removed=None2026.024,000
SAC+VDAlgorithm=SAC, Critic=VD2026.023,850.4
SACNoise Variance=0.0012025.123,761.98
SAC BaselineState Dim Removed=162026.023,750
T-REXState Dim Removed=162026.023,662
TD3 - VanillaAlgorithm Variant=Vanilla, Base Algorithm=TD32026.033,570
TrexState Dim Removed=162026.023,536
SAC+IQNAlgorithm=SAC, Critic=IQN2026.023,487.4
BaselineState Dim Removed=162026.023,474
Causal PBRSState Dim Removed=132026.023,389
CQLState Dim Removed=162026.023,190
CQLState Dim Removed=162026.023,169
SAC - VanillaAlgorithm Variant=Vanilla, Base Algorithm=SAC2026.033,157
Causal PBRSState Dim Removed=132026.023,093
SAC BaselineState Dim Removed=132026.023,084
BaselineState Dim Removed=132026.023,082
Causal PBRSState Dim Removed=162026.022,963
T-REXState Dim Removed=132026.022,830
Causal PBRSState Dim Removed=162026.022,818
CQLState Dim Removed=132026.022,792
CQLState Dim Removed=132026.022,781
TrexState Dim Removed=132026.022,663
SAC+VFAlgorithm=SAC, Critic=VF2026.022,650.3
SACNoise Variance=0.012025.122,619.72
SAC+DSACAlgorithm=SAC, Critic=DSAC2026.022,013.2
Recurrent SACState Dim Removed=162026.021,225
Recurrent SACState Dim Removed=162026.021,221
Recurrent SACState Dim Removed=132026.02994
RSA2C-KMENoise Variance=02025.12960.36
RSA2C-CMENoise Variance=0.012025.12959.65
RSA2C-KMENoise Variance=0.012025.12958.54
RSA2C-KMENoise Variance=0.0012025.12957.37
Recurrent SACState Dim Removed=132026.02957
RSA2C-KMENoise Variance=0.0052025.12954.13
RSA2C-CMENoise Variance=0.0012025.12953.84
RSA2C-CMENoise Variance=0.0052025.12948.86
RSA2C-CMENoise Variance=02025.12934.15
DDPG - VanillaAlgorithm Variant=Vanilla, Base Algorithm=DDPG2026.03610
PPO - H-EARSAlgorithm Variant=H-EARS, Base Algorithm=PPO2026.03501
DDPG - H-EARSAlgorithm Variant=H-EARS, Base Algorithm=DDPG2026.03456
PPO - VanillaAlgorithm Variant=Vanilla, Base Algorithm=PPO2026.03376
PPONoise Variance=0.0012025.12155.64
PPONoise Variance=0.0052025.1232.47
PPONoise Variance=02025.1217.34
PPONoise Variance=0.012025.12-11.15