קידום רכיבי תכנון: לקחים מ-160,000 רצי טריינינג

תקציר מקורי באנגליתarXiv:2609.13730v1 Announce Type: new Abstract: 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 dominates: aggregate performance among the strongest methods is often close, but the leaders differ substantially across environments. We find that proper h