ポリシーデコレーター：大規模ポリシーモデルのためのモデル非依存オンライン改良
Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model
模倣学習で訓練済みの大規模ポリシーに対し、モデル非依存の残差ポリシーをオンラインで学習させて性能を安定かつサンプル効率よく向上させる手法を提案。
著者: Xiu Yuan, Tongzhou Mu, Stone Tao, Yunhao Fang, Mengke Zhang, Hao Su
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
Recent advancements in robot learning have used imitation learning with large models and extensive demonstrations to develop effective policies. However, these models are often limited by the quantity, quality, and diversity of demonstrations. This paper explores improving offline-trained imitation learning models through online interactions with the environment. We introduce Policy Decorator, which uses a model-agnostic residual policy to refine large imitation learning models during online interactions. By implementing controlled exploration strategies, Policy Decorator enables stable, sample-efficient online learning. Our evaluation spans eight tasks across two benchmarks-ManiSkill and Adroit-and involves two state-of-the-art imitation learning models (Behavior Transformer and Diffusion Policy). The results show Policy Decorator effectively improves the offline-trained policies and preserves the smooth motion of imitation learning models, avoiding the erratic behaviors of pure RL policies. See our project page (https://policydecorator.github.io) for videos.
