OAT:有序动作标记化
OAT: Ordered Action Tokenization
AI总结:
OAT通过有序动作标记化方法,实现高压缩性和因果有序的标记空间,提升机器人动作生成的灵活性和性能。
摘要:
自回归策略为可扩展的机器人学习提供了一个有吸引力的基础,通过使离散抽象、逐个标记推理和灵活的推断成为可能。然而,将自回归建模应用于连续机器人动作需要一个有效的动作标记化方案。现有方法要么依赖于分析离散化方法,产生 prohibitively 长的标记序列,要么使用学习的潜在标记器,缺乏结构,限制了它们与下一个标记预测的兼容性。在本文中,我们识别了动作标记化所需的三个标准——高压缩性、总可解码性和因果有序的标记空间,并引入了有序动作标记化(OAT),一种满足所有三个标准的学习动作标记器。OAT 使用带有寄存器的变压器、有限标量量化和诱导顺序的训练机制,将动作块离散化为有序的标记序列。所得到的标记空间自然地与自回归生成相容,并启用基于前缀的去标记化,从而在推理成本和动作保真度之间取得任何时间的权衡。在超过20个任务上,跨越四个模拟基准和现实世界设置,配备OAT的自回归策略在之前标记化方案和扩散基线方面表现一致更优,同时在推理时间提供显著更大的灵活性。
英文摘要:
Autoregressive policies offer a compelling foundation for scalable robot learning by enabling discrete abstraction, token-level reasoning, and flexible inference. However, applying autoregressive modeling to continuous robot actions requires an effective action tokenization scheme. Existing approaches either rely on analytical discretization methods that produce prohibitively long token sequences, or learned latent tokenizers that lack structure, limiting their compatibility with next-token prediction. In this work, we identify three desiderata for action tokenization - high compression, total decodability, and a left-to-right causally ordered token space - and introduce Ordered Action Tokenization (OAT), a learned action tokenizer that satisfies all three. OAT discretizes action chunks into an ordered sequence of tokens using transformer with registers, finite scalar quantization, and ordering-inducing training mechanisms. The resulting token space aligns naturally with autoregressive generation and enables prefix-based detokenization, yielding an anytime trade-off between inference cost and action fidelity. Across more than 20 tasks spanning four simulation benchmarks and real-world settings, autoregressive policies equipped with OAT consistently outperform prior tokenization schemes and diffusion-based baselines, while offering significantly greater flexibility at inference time.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。