精确学习算术的可微代理
Exact Learning of Arithmetic with Differentiable Agents
AI总结：
本文提出通过可微有限状态转录机实现精确算术学习，展示模型在微小数据集上可泛化至长输入的无误差表现。
摘要：
我们探索基于梯度的方法实现精确算法学习的可能性，并介绍了一种可微框架，该框架能够在算术任务上实现强大的长度泛化能力。我们的方法聚焦于可微有限状态转录机（DFSTs），这是一种图灵完备的模型家族，通过实现常精度、常时间生成以及端到端对数并行可微训练，避免了先前架构的缺陷。利用专家代理的策略轨迹观察，我们训练DFSTs执行二进制和十进制加法和乘法。令人惊讶的是，模型在微小数据集上训练后，能够无误差地泛化到比训练示例长数千倍的输入。这些结果表明，通过结构化中间监督训练可微代理，可能为精确基于梯度的算法技能学习铺平道路。代码可在https://github.com/dngfra/differentiable-exact-algorithmic-learner.git获取。
英文摘要：
We explore the possibility of exact algorithmic learning with gradient-based methods and introduce a differentiable framework capable of strong length generalization on arithmetic tasks. Our approach centers on Differentiable Finite-State Transducers (DFSTs), a Turing-complete model family that avoids the pitfalls of prior architectures by enabling constant-precision, constant-time generation, and end-to-end log-parallel differentiable training. Leveraging policy-trajectory observations from expert agents, we train DFSTs to perform binary and decimal addition and multiplication. Remarkably, models trained on tiny datasets generalize without error to inputs thousands of times longer than the training examples. These results show that training differentiable agents on structured intermediate supervision could pave the way towards exact gradient-based learning of algorithmic skills. Code available at \href{https://github.com/dngfra/differentiable-exact-algorithmic-learner.git}{https://github.com/dngfra/differentiable-exact-algorithmic-learner.git}.
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。
