Reinforcement Learning on Walker2D v5
6,335.5Average ReturnTD3+DBC(*)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| TD3+DBC(*)Algorithm=TD3, Critic=DBC2026.02 | 6,335.5 | — | |
| SAC+DBC(*)Algorithm=SAC, Critic=DBC2026.02 | 6,138.2 | — | |
| SAC+TQCAlgorithm=SAC, Critic=TQC2026.02 | 5,802.6 | — | |
| QVPO+DBC(*)Algorithm=QVPO, Critic=DBC2026.02 | 5,448.1 | — | |
| TD3+CDQAlgorithm=TD3, Critic=CDQ2026.02 | 5,093.7 | — | |
| QVPO+CDQAlgorithm=QVPO, Critic=CDQ2026.02 | 4,986.3 | — | |
| SAC+CDQAlgorithm=SAC, Critic=CDQ2026.02 | 4,854.4 | — | |
| SAC+IQNAlgorithm=SAC, Critic=IQN2026.02 | 4,766.5 | — | |
| T-REXState Dim Removed=102026.02 | 4,417 | — | |
| TrexState Dim Removed=102026.02 | 4,385 | — | |
| Causal PBRSState Dim Removed=82026.02 | 4,295 | — | |
| Full State SACState Dim Removed=None2026.02 | 4,050 | — | |
| Full State SACState Dim Removed=None2026.02 | 4,050 | — | |
| T-REXState Dim Removed=62026.02 | 4,045 | — | |
| SAC BaselineState Dim Removed=62026.02 | 3,981 | — | |
| Causal PBRSState Dim Removed=102026.02 | 3,950 | — | |
| BaselineState Dim Removed=102026.02 | 3,925 | — | |
| SAC BaselineState Dim Removed=102026.02 | 3,925 | — | |
| Causal PBRSState Dim Removed=62026.02 | 3,899 | — | |
| BaselineState Dim Removed=62026.02 | 3,893 | — | |
| Causal PBRSState Dim Removed=62026.02 | 3,884 | — | |
| Causal PBRSState Dim Removed=102026.02 | 3,814 | — | |
| CQLState Dim Removed=82026.02 | 3,766 | — | |
| CQLState Dim Removed=82026.02 | 3,708 | — | |
| SAC BaselineState Dim Removed=82026.02 | 3,640 | — | |
| Causal PBRSState Dim Removed=82026.02 | 3,632 | — | |
| TrexState Dim Removed=62026.02 | 3,603 | — | |
| CQLState Dim Removed=102026.02 | 3,600 | — | |
| BaselineState Dim Removed=82026.02 | 3,580 | — | |
| CQLState Dim Removed=102026.02 | 3,424 | — | |
| SAC+DSACAlgorithm=SAC, Critic=DSAC2026.02 | 3,297.4 | — | |
| CQLState Dim Removed=62026.02 | 3,243 | — | |
| CQLState Dim Removed=62026.02 | 3,132 | — | |
| T-REXState Dim Removed=82026.02 | 2,830 | — | |
| TrexState Dim Removed=82026.02 | 2,663 | — | |
| SAC+VFAlgorithm=SAC, Critic=VF2026.02 | 2,626.4 | — | |
| SAC+VDAlgorithm=SAC, Critic=VD2026.02 | 2,533.9 | — | |
| Recurrent SACState Dim Removed=62026.02 | 2,210 | — | |
| Recurrent SACState Dim Removed=62026.02 | 2,181 | — | |
| Recurrent SACState Dim Removed=102026.02 | 1,351 | — | |
| Recurrent SACState Dim Removed=102026.02 | 1,124 | — | |
| Recurrent SACState Dim Removed=82026.02 | 1,105 | — | |
| Recurrent SACState Dim Removed=82026.02 | 942 | — | |
| RPIDDPG2025.06 | 319.9 | 245 | |
| DDPG2025.06 | 200.3 | 165.7 |