HQL balances one-step and multi-step returns for long horizons
A multi-step target is kept only when a dataset action beats best-of-N behavior-cloned actions.
34
Product
OGBench
- Mentions · 7d1
- Mentions · 30d1
- All mentions4
- First seenSep 24, 2026
- Last mentioned5d ago
Timeline
4 articles · newest firstQ-Learning with Scalar Adjoint Matching
SQAM fine-tunes flow policies with a scalar adjoint, beating baselines by 18 to 35 points on hard OGBench tasks.
48
Q-Learning with Scalar Adjoint Matching
SQAM fine-tunes flow policies with a scalar adjoint, beating baselines by 18–35 points on hard OGBench domains.
48
AD-WM: Action-Discriminative World Models for Counterfactual Model Predictive Control
AD-WM improves counterfactual planning by preserving action information, raising hard-start success from 3.7% to 52%.
48
Appears with
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.