Continuous Control on DMC Reacher Easy
984.65RewardSmODE-SAC
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| SmODE-SACBase Algorithm=SAC2026.05 | 984.65 | 0.4 | 0.62 | 0.8 | 1.29 | 1.32 | 1.82 | 0.75 | |
| DWS-SACBase Algorithm=SAC2026.05 | 979.75 | 0.04 | 0.08 | 0.09 | 0.18 | 0.16 | 0.7 | 0.09 | |
| ActionChunk-SACBase Algorithm=SAC2026.05 | 924.95 | 0.03 | 0.05 | 0.06 | 0.12 | 0.1 | 0.89 | 0.11 | |
| DWS-TD3Base Algorithm=TD32026.05 | 922.65 | 0.12 | 0.19 | 0.24 | 0.57 | 0.64 | 1.56 | 0.33 | |
| SmODE-TD3Base Algorithm=TD32026.05 | 914.22 | 0.54 | 1.01 | 1.2 | 1.98 | 2.03 | 1.71 | 1.08 | |
| L2C2-TD3Base Algorithm=TD32026.05 | 911.35 | 0.57 | 0.84 | 1.15 | 1.76 | 1.82 | 1.58 | 0.93 | |
| Vanilla-TD3Base Algorithm=TD32026.05 | 908.2 | 0.68 | 1.03 | 1.35 | 2.15 | 2.5 | 1.91 | 1.29 | |
| L2C2-SACBase Algorithm=SAC2026.05 | 883.6 | 0.03 | 0.05 | 0.06 | 0.08 | 0.08 | 0.84 | 0.09 | |
| LipsNet++-TD3Base Algorithm=TD32026.05 | 794.5 | 0.54 | 0.81 | 1.09 | 1.67 | 1.7 | 1.46 | 0.88 | |
| Vanilla-SACBase Algorithm=SAC2026.05 | 792.05 | 0.41 | 0.65 | 0.83 | 1.4 | 1.34 | 1.9 | 0.69 | |
| ActionChunk-TD3Base Algorithm=TD32026.05 | 74.6 | — | — | — | — | — | — | — | |
| LipsNet++-SACBase Algorithm=SAC2026.05 | 57.2 | — | — | — | — | — | — | — |