Offline Reinforcement Learning on Hopper Medium (Noise 5)
70.67Normalized ReturnI-TAP
Evaluation Results
| Method | Links | |
|---|---|---|
| I-TAPModel Category=Model-Based2026.02 | 70.67 | |
| 1R2RModel Category=Model-Based2026.02 | 68.25 | |
| I-TAPModel Category=Model-Based2026.02 | 67.8 | |
| L-MAPModel Category=Model-Based2026.02 | 60.76 | |
| L-MAPModel Category=Model-Based2026.02 | 59.05 | |
| DTModel Category=Model-Free2026.02 | 55.91 | |
| CQLModel Category=Model-Free2026.02 | 51.7 | |
| IQLModel Category=Model-Free2026.02 | 49.69 | |
| TAPModel Category=Model-Based2026.02 | 48.69 | |
| CQLModel Category=Model-Free2026.02 | 45.21 | |
| TAPModel Category=Model-Based2026.02 | 43.93 | |
| IQLModel Category=Model-Free2026.02 | 43.27 | |
| DTModel Category=Model-Free2026.02 | 35.17 | |
| 1R2RModel Category=Model-Based2026.02 | 33.99 |