SOURCE-LINKED INTELLIGENCE

JumpStart Your Policy Learning with Lessons from 160,000 Training Runs

arXiv · AI, language, vision and robotics · article · Sep 12, 2026 · UTC

Reliable progress in offline policy learning depends on careful reporting, well-tuned baselines, and evaluation across diverse conditions. Prior work has shown that results can be sensitive to reporting choices, hyperparameter tuning, and dataset properties, but these sources of variability have not been systematically investigated together at the scale needed to understand how they shape conclusions. To address this gap, we present a large-scale empirical study of offline reinforcement and imitation learning, training over 160,000 policies across 114 datasets. At this scale, no algorithm domi

Read original source ↗ Open in workspace

recordType

paper

region

Global