D4RL Kitchen
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Offline Reinforcement Learning | D4RL Kitchen-mixed v0 (test) | Normalized Score67.5 | 18 | |
| Offline Reinforcement Learning | D4RL Kitchen kitchen-partial v0 (test) | Normalized Score75.8 | 18 | |
| Offline Reinforcement Learning | D4RL kitchen-complete v0 (test) | Normalized Score84 | 12 | |
| Offline Reinforcement Learning | D4RL Kitchen (kitchen-complete) | Normalized Score78.4 | 9 | |
| Offline Reinforcement Learning | D4RL Kitchen manipulation v0 | Runtime (s)0.01 | 6 | |
| Low-level policy imitation | D4RL Kitchen (test) | MKSH MSE1.91 | 5 | |
| kitchen-partial (split 2) | D4RL Kitchen (partial) | Normalized Return63.7 | 4 |
Showing 7 of 7 rows