Reinforcement Learning on DeepMind Control Suite walker_walk medium
902Episode ReturnFull State
Evaluation results
| Method | Links | |
|---|---|---|
| Full State2026.03 | 902 | |
| IBD2026.03 | 792 | |
| Oracle2026.03 | 785 | |
| Cond. MI2026.03 | 220 | |
| MI Select2026.03 | 129 | |
| Var Select2026.03 | 84 |
| Method | Links | |
|---|---|---|
| Full State2026.03 | 902 | |
| IBD2026.03 | 792 | |
| Oracle2026.03 | 785 | |
| Cond. MI2026.03 | 220 | |
| MI Select2026.03 | 129 | |
| Var Select2026.03 | 84 |