Reinforcement Learning on Hopper v5
3,732.5Average ReturnSAC+DBC(*)
Evaluation Results
| Method | Links | |
|---|---|---|
| SAC+DBC(*)Algorithm=SAC, Critic=DBC2026.02 | 3,732.5 | |
| QVPO+DBC(*)Algorithm=QVPO, Critic=DBC2026.02 | 3,721.3 | |
| SAC+TQCAlgorithm=SAC, Critic=TQC2026.02 | 3,704.6 | |
| TD3+DBC(*)Algorithm=TD3, Critic=DBC2026.02 | 3,685.7 | |
| SAC+CDQAlgorithm=SAC, Critic=CDQ2026.02 | 3,630.5 | |
| TD3+CDQAlgorithm=TD3, Critic=CDQ2026.02 | 3,596.2 | |
| Causal PBRSState Dim Removed=32026.02 | 3,582 | |
| Causal PBRSState Dim Removed=32026.02 | 3,582 | |
| QVPO+CDQAlgorithm=QVPO, Critic=CDQ2026.02 | 3,582 | |
| SAC+DSACAlgorithm=SAC, Critic=DSAC2026.02 | 3,522.9 | |
| Full State SACState Dim Removed=None2026.02 | 3,500 | |
| Full State SACState Dim Removed=None2026.02 | 3,500 | |
| Recurrent SACState Dim Removed=7,8,9,102026.02 | 3,468 | |
| SAC - H-EARSAlgorithm Variant=H-EARS, Base Algorithm=SAC2026.03 | 3,354 | |
| SAC BaselineState Dim Removed=52026.02 | 3,321 | |
| SAC+VFAlgorithm=SAC, Critic=VF2026.02 | 3,310.4 | |
| SAC+IQNAlgorithm=SAC, Critic=IQN2026.02 | 3,301.8 | |
| BaselineState Dim Removed=52026.02 | 3,298 | |
| SAC BaselineState Dim Removed=32026.02 | 3,283 | |
| BaselineState Dim Removed=32026.02 | 3,281 | |
| Causal PBRSState Dim Removed=52026.02 | 3,183 | |
| Causal PBRSState Dim Removed=52026.02 | 3,055 | |
| Recurrent SACState Dim Removed=7,8,9,102026.02 | 3,050 | |
| Causal PBRSState Dim Removed=72026.02 | 3,011 | |
| SAC BaselineState Dim Removed=72026.02 | 2,935 | |
| BaselineState Dim Removed=72026.02 | 2,885 | |
| Recurrent SACState Dim Removed=52026.02 | 2,878 | |
| T-REXState Dim Removed=52026.02 | 2,862 | |
| Causal PBRSState Dim Removed=72026.02 | 2,793 | |
| T-REXState Dim Removed=32026.02 | 2,780 | |
| Causal PBRSState Dim Removed=22026.02 | 2,762 | |
| Causal PBRSState Dim Removed=22026.02 | 2,729 | |
| Recurrent SACState Dim Removed=52026.02 | 2,711 | |
| Recurrent SACState Dim Removed=72026.02 | 2,693 | |
| TrexState Dim Removed=32026.02 | 2,671 | |
| TD3 - H-EARSAlgorithm Variant=H-EARS, Base Algorithm=TD32026.03 | 2,641 | |
| TrexState Dim Removed=52026.02 | 2,605 | |
| T-REXState Dim Removed=72026.02 | 2,550 | |
| SAC - VanillaAlgorithm Variant=Vanilla, Base Algorithm=SAC2026.03 | 2,520 | |
| Recurrent SACState Dim Removed=72026.02 | 2,448 | |
| Recurrent SACState Dim Removed=22026.02 | 2,432 | |
| Recurrent SACState Dim Removed=22026.02 | 2,407 | |
| TD3 - VanillaAlgorithm Variant=Vanilla, Base Algorithm=TD32026.03 | 2,364 | |
| Causal PBRSState Dim Removed=12026.02 | 2,252 | |
| Causal PBRSState Dim Removed=12026.02 | 2,199 | |
| TrexState Dim Removed=72026.02 | 2,081 | |
| SAC BaselineState Dim Removed=12026.02 | 2,073 | |
| BaselineState Dim Removed=12026.02 | 2,005 | |
| Recurrent SACState Dim Removed=5,62026.02 | 1,978 | |
| CQLState Dim Removed=12026.02 | 1,778 | |
| Recurrent SACState Dim Removed=5,62026.02 | 1,645 | |
| PPO - VanillaAlgorithm Variant=Vanilla, Base Algorithm=PPO2026.03 | 1,621 | |
| Recurrent SACState Dim Removed=32026.02 | 1,601 | |
| CQLState Dim Removed=12026.02 | 1,592 | |
| DDPG - H-EARSAlgorithm Variant=H-EARS, Base Algorithm=DDPG2026.03 | 1,580 | |
| PPO - H-EARSAlgorithm Variant=H-EARS, Base Algorithm=PPO2026.03 | 1,568 | |
| DDPG - VanillaAlgorithm Variant=Vanilla, Base Algorithm=DDPG2026.03 | 1,490 | |
| CQLState Dim Removed=32026.02 | 1,478 | |
| BaselineState Dim Removed=22026.02 | 1,450 | |
| SAC BaselineState Dim Removed=22026.02 | 1,450 | |
| Causal PBRSState Dim Removed=7,8,9,102026.02 | 1,442 | |
| Recurrent SACState Dim Removed=32026.02 | 1,379 | |
| TrexState Dim Removed=22026.02 | 1,344 | |
| T-REXState Dim Removed=22026.02 | 1,344 | |
| CQLState Dim Removed=32026.02 | 1,321 | |
| T-REXState Dim Removed=12026.02 | 1,276 | |
| CQLState Dim Removed=72026.02 | 1,245 | |
| CQLState Dim Removed=72026.02 | 1,239 | |
| TrexState Dim Removed=12026.02 | 1,233 | |
| Causal PBRSState Dim Removed=7,8,9,102026.02 | 1,228 | |
| CQLState Dim Removed=5,62026.02 | 1,143 | |
| CQLState Dim Removed=22026.02 | 1,096 | |
| CQLState Dim Removed=5,62026.02 | 1,060 | |
| SAC+VDAlgorithm=SAC, Critic=VD2026.02 | 1,052.7 | |
| CQLState Dim Removed=52026.02 | 1,038 | |
| Causal PBRSState Dim Removed=5,62026.02 | 1,037 | |
| CQLState Dim Removed=52026.02 | 1,035 | |
| CQLState Dim Removed=22026.02 | 1,018 | |
| Causal PBRSState Dim Removed=5,62026.02 | 903 | |
| T-REXState Dim Removed=5,62026.02 | 823 | |
| TrexState Dim Removed=5,62026.02 | 737 | |
| SAC BaselineState Dim Removed=5,62026.02 | 655 | |
| BaselineState Dim Removed=5,62026.02 | 645 | |
| Recurrent SACState Dim Removed=12026.02 | 562 | |
| CQLState Dim Removed=1,2,3,42026.02 | 557 | |
| CQLState Dim Removed=1,2,3,42026.02 | 528 | |
| Recurrent SACState Dim Removed=12026.02 | 490 | |
| Recurrent SACState Dim Removed=1,2,3,42026.02 | 460 | |
| CQLState Dim Removed=7,8,9,102026.02 | 422 | |
| CQLState Dim Removed=7,8,9,102026.02 | 409 | |
| SAC BaselineState Dim Removed=7,8,9,102026.02 | 372 | |
| BaselineState Dim Removed=7,8,9,102026.02 | 367 | |
| TrexState Dim Removed=7,8,9,102026.02 | 367 | |
| T-REXState Dim Removed=7,8,9,102026.02 | 367 | |
| Recurrent SACState Dim Removed=1,2,3,42026.02 | 353 | |
| T-REXState Dim Removed=1,2,3,42026.02 | 310 | |
| Causal PBRSState Dim Removed=1,2,3,42026.02 | 305 | |
| SAC BaselineState Dim Removed=1,2,3,42026.02 | 304 | |
| TrexState Dim Removed=1,2,3,42026.02 | 303 | |
| Causal PBRSState Dim Removed=1,2,3,42026.02 | 301 |