Offline Reinforcement Learning on HalfCheetah Expert
1,002.09Episodic ReturnBCQ
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| BCQK_act=2562026.02 | 1,002.09 | — | |
| AWACK_act=2562026.02 | 29.14 | — | |
| BCQ2026.02 | 10.33 | — | |
| AWAC2026.02 | 2.49 | — | |
| QDFM2026.02 | 1.26 | — | |
| GreedyQ2026.02 | -0.31 | — | |
| AWBC2026.02 | -0.71 | — | |
| CQL2026.02 | -1.19 | — | |
| QDFMK_act=2562026.02 | -123.18 | — | |
| GreedyQK_act=2562026.02 | -319.23 | — | |
| AWBCK_act=2562026.02 | -367.81 | — | |
| CQLK_act=2562026.02 | -428.26 | — | |
| BOSA2025.12 | — | 3.6 | |
| DARA2025.12 | — | 2.9 | |
| DVDF-IGDF2025.12 | — | 5.9 | |
| DVDF-OTDF2025.12 | — | 15.4 | |
| IGDF2025.12 | — | 6.2 | |
| IQL2025.12 | — | 4.9 | |
| OTDF2025.12 | — | 10.7 |