Model card
Diffusion-QL.
Twitter / Cornellopen-sourceDiffusion model policy trained with Q-learning regularization for offline RL1 current SOTA
Wang et al. ICLR 2023. Demonstrated strong performance by using diffusion as policy class.
§ 02 · Benchmarks
Every benchmark Diffusion-QL has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | d4rl-halfcheetah-medium | — | normalized_return | 51.1% | #1 | 2026-04-20 | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 06 · Sources & freshness
Where these numbers come from.
codesota-api
1
result
0 of 1 rows marked verified.