Jul 2026
Adaptive FastOPD: Progress-Aware Rollout Horizon Expansion for Efficient On-Policy Distillation
Adaptive FastOPD is proposed, a progress-aware strategy that expands the rollout horizon only when learning near the current boundary region has plateaued and the current horizon is sufficiently utilized, and remains robust across a range of hyperparameter settings.
Qian Tan, Huaifei Liang, Xuanyu Zhu et al.
· arXiv.org · 2 citations