Reinforcement Learning on Ant v5
6,633.8Average ReturnQVPO+DBC(*)
Evaluation Results
| Method | Links | |
|---|---|---|
| QVPO+DBC(*)Algorithm=QVPO, Critic=DBC2026.02 | 6,633.8 | |
| SAC+DBC(*)Algorithm=SAC, Critic=DBC2026.02 | 6,501.4 | |
| QVPO+CDQAlgorithm=QVPO, Critic=CDQ2026.02 | 6,373.2 | |
| SAC+TQCAlgorithm=SAC, Critic=TQC2026.02 | 6,342.6 | |
| SAC+CDQAlgorithm=SAC, Critic=CDQ2026.02 | 6,121.8 | |
| TD3+DBC(*)Algorithm=TD3, Critic=DBC2026.02 | 5,306 | |
| SACNoise Variance=02025.12 | 4,477.33 | |
| TD3+CDQAlgorithm=TD3, Critic=CDQ2026.02 | 4,257 | |
| SAC - H-EARSAlgorithm Variant=H-EARS, Base Algorithm=SAC2026.03 | 4,183 | |
| TD3 - H-EARSAlgorithm Variant=H-EARS, Base Algorithm=TD32026.03 | 4,125 | |
| SACNoise Variance=0.0052025.12 | 4,067.61 | |
| Full State SACState Dim Removed=None2026.02 | 4,000 | |
| Full State SACState Dim Removed=None2026.02 | 4,000 | |
| SAC+VDAlgorithm=SAC, Critic=VD2026.02 | 3,850.4 | |
| SACNoise Variance=0.0012025.12 | 3,761.98 | |
| SAC BaselineState Dim Removed=162026.02 | 3,750 | |
| T-REXState Dim Removed=162026.02 | 3,662 | |
| TD3 - VanillaAlgorithm Variant=Vanilla, Base Algorithm=TD32026.03 | 3,570 | |
| TrexState Dim Removed=162026.02 | 3,536 | |
| SAC+IQNAlgorithm=SAC, Critic=IQN2026.02 | 3,487.4 | |
| BaselineState Dim Removed=162026.02 | 3,474 | |
| Causal PBRSState Dim Removed=132026.02 | 3,389 | |
| CQLState Dim Removed=162026.02 | 3,190 | |
| CQLState Dim Removed=162026.02 | 3,169 | |
| SAC - VanillaAlgorithm Variant=Vanilla, Base Algorithm=SAC2026.03 | 3,157 | |
| Causal PBRSState Dim Removed=132026.02 | 3,093 | |
| SAC BaselineState Dim Removed=132026.02 | 3,084 | |
| BaselineState Dim Removed=132026.02 | 3,082 | |
| Causal PBRSState Dim Removed=162026.02 | 2,963 | |
| T-REXState Dim Removed=132026.02 | 2,830 | |
| Causal PBRSState Dim Removed=162026.02 | 2,818 | |
| CQLState Dim Removed=132026.02 | 2,792 | |
| CQLState Dim Removed=132026.02 | 2,781 | |
| TrexState Dim Removed=132026.02 | 2,663 | |
| SAC+VFAlgorithm=SAC, Critic=VF2026.02 | 2,650.3 | |
| SACNoise Variance=0.012025.12 | 2,619.72 | |
| SAC+DSACAlgorithm=SAC, Critic=DSAC2026.02 | 2,013.2 | |
| Recurrent SACState Dim Removed=162026.02 | 1,225 | |
| Recurrent SACState Dim Removed=162026.02 | 1,221 | |
| Recurrent SACState Dim Removed=132026.02 | 994 | |
| RSA2C-KMENoise Variance=02025.12 | 960.36 | |
| RSA2C-CMENoise Variance=0.012025.12 | 959.65 | |
| RSA2C-KMENoise Variance=0.012025.12 | 958.54 | |
| RSA2C-KMENoise Variance=0.0012025.12 | 957.37 | |
| Recurrent SACState Dim Removed=132026.02 | 957 | |
| RSA2C-KMENoise Variance=0.0052025.12 | 954.13 | |
| RSA2C-CMENoise Variance=0.0012025.12 | 953.84 | |
| RSA2C-CMENoise Variance=0.0052025.12 | 948.86 | |
| RSA2C-CMENoise Variance=02025.12 | 934.15 | |
| DDPG - VanillaAlgorithm Variant=Vanilla, Base Algorithm=DDPG2026.03 | 610 | |
| PPO - H-EARSAlgorithm Variant=H-EARS, Base Algorithm=PPO2026.03 | 501 | |
| DDPG - H-EARSAlgorithm Variant=H-EARS, Base Algorithm=DDPG2026.03 | 456 | |
| PPO - VanillaAlgorithm Variant=Vanilla, Base Algorithm=PPO2026.03 | 376 | |
| PPONoise Variance=0.0012025.12 | 155.64 | |
| PPONoise Variance=0.0052025.12 | 32.47 | |
| PPONoise Variance=02025.12 | 17.34 | |
| PPONoise Variance=0.012025.12 | -11.15 |