Temporal action abstractions, along with belief state representations, are a
powerful knowledge sharing mechanism for sequential decision making. In this
work, we propose a novel view that treats inducing temporal action abstractions
as a sequence compression problem. To do so, we bring a subtle but critical
component of LLM training pipelines -- input tokenization via byte pair
encoding (BPE) -- to the seemingly distant task of learning skills of variable
time span in continuous control domains. We introduce an approach called
Primitive Sequence Encoding (PRISE) that combines continuous action
quantization with BPE to learn powerful action abstractions. We empirically
show that high-level skills discovered by PRISE from a multitask set of robotic
manipulation demonstrations significantly boost the performance of both
multitask imitation learning as well as few-shot imitation learning on unseen
tasks. Our code will be released at this https URL

本研究提出了一种新颖的方法，将引发时间动作抽象视为序列压缩问题，结合连续控制领域中连续动作量化和字节对编码（BPE）的输入标记化，提出了名为 PRISE 的方法，通过多任务机器人操作示范，从中发现的高级技能显著提高了多任务模仿学习以及少样本模仿学习在未知任务上的表现。

PRISE：学习时间动作抽象作为一个序列压缩问题

PRISE: Learning Temporal Action Abstractions as a Sequence Compression  Problem

The sequence length along the time axis is often the dominant factor of the
computation in speech processing. Works have been proposed to reduce the
sequence length for lowering the computational cost in self-supervised speech
models. However, different downstream tasks have different tolerance of
sequence compressing, so a model that produces a fixed compressing rate may not
fit all tasks. In this work, we introduce a once-for-all (OFA) sequence
compression framework for self-supervised speech models that supports a
continuous range of operating compressing rates. The framework is evaluated on
various tasks, showing marginal degradation compared to the fixed compressing
rate variants with a smooth performance-efficiency trade-off. We further
explore adaptive compressing rate learning, demonstrating the ability to select
task-specific preferred frame periods without needing a grid search.

本研究提出了一种可以在多种下游任务中调节压缩率的模型压缩方法，该方法可以在保证语音模型性能的前提下，减小计算成本并且不需要通过网格搜索来确定不同任务的压缩率。

针对自监督语音模型的一次性序列压缩

Once-for-All Sequence Compression for Self-Supervised Speech Models

With the success of language pretraining, it is highly desirable to develop
more efficient architectures of good scalability that can exploit the abundant
unlabeled data at a lower cost. To improve the efficiency, we examine the
much-overlooked redundancy in maintaining a full-length token-level
presentation, especially for tasks that only require a single-vector
presentation of the sequence. With this intuition, we propose
Funnel-Transformer which gradually compresses the sequence of hidden states to
a shorter one and hence reduces the computation cost. More importantly, by
re-investing the saved FLOPs from length reduction in constructing a deeper or
wider model, we further improve the model capacity. In addition, to perform
token-level predictions as required by common pretraining objectives,
Funnel-Transformer is able to recover a deep representation for each token from
the reduced hidden sequence via a decoder. Empirically, with comparable or
fewer FLOPs, Funnel-Transformer outperforms the standard Transformer on a wide
variety of sequence-level prediction tasks, including text classification,
language understanding, and reading comprehension. The code and pretrained
checkpoints are available at this https URL

本研究提出了 Funnel-Transformer 模型，利用序列压缩来提升模型效率，在保证单向量序列表征的前提下极大地减少了计算成本。通过在模型构建时重新投资在长度缩短中节省下来的 FLOPs，进一步提高了模型容量。实验表明，Funnel-Transformer 在一系列序列级别的预测任务上表现优秀，包括文本分类、语言理解和阅读理解。