We present Masked Generative Policy (MGP), a novel framework for visuomotor imitation learning. We represent actions as discrete tokens, and train a conditional masked transformer that generates tokens in parallel and then rapidly refines only low-confidence tokens. We further propose two new sampling paradigms: MGP-Short, which performs parallel masked generation with score-based refinement for Markovian tasks, and MGP-Long, which predicts full trajectories in a single pass and dynamically refines low-confidence action tokens based on new observations. With globally coherent prediction and robust adaptive execution capabilities, MGP-Long enables reliable control on complex and non-Markovian tasks that prior methods struggle with. Extensive evaluations on 150 robotic manipulation tasks spanning the Meta-World and LIBERO benchmarks show that MGP achieves both rapid inference and superior success rates compared to state-of-the-art diffusion and autoregressive policies. Specifically, MGP increases the average success rate by 9% across 150 tasks while cutting per-sequence inference time by up to 35x. It further improves the average success rate by 60% in dynamic and missing-observation environments, and solves two non-Markovian scenarios where other state-of-the-art methods fail.

翻译：本文提出掩码生成策略（MGP），一种用于视觉运动模仿学习的新型框架。我们将动作表示为离散标记，并训练一个条件掩码Transformer模型，该模型并行生成标记，随后仅对低置信度标记进行快速优化。我们进一步提出两种新型采样范式：MGP-Short采用基于得分的优化机制进行并行掩码生成，适用于马尔可夫任务；MGP-Long则通过单次前向预测完整轨迹，并依据新观测动态优化低置信度动作标记。凭借全局一致性预测与鲁棒自适应执行能力，MGP-Long能够在现有方法难以处理的复杂非马尔可夫任务中实现可靠控制。在涵盖Meta-World与LIBERO基准测试的150项机器人操作任务上的广泛实验表明，相较于最先进的扩散策略与自回归策略，MGP在实现快速推理的同时获得了更高的成功率。具体而言，MGP在150项任务中将平均成功率提升9%，同时将单序列推理时间缩短达35倍。在动态与观测缺失环境中，其平均成功率进一步提升60%，并在两项其他前沿方法无法处理的非马尔可夫场景中取得突破。