mlsanityData to 7 Oct 2026

Learning to solve arithmetic problems with a virtual abacus

arXiv 2301.06870 ↗First posted 17 Jan 2023cs.LG cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Acquiring mathematical skills is considered a key challenge for modern Artificial Intelligence systems. Inspired by the way humans discover numerical knowledge, here we introduce a deep reinforcement learning framework that allows to simulate how cognitive agents could gradually learn to solve arithmetic problems by interacting with a virtual abacus. The proposed model successfully learn to perform multi-digit additions and subtractions, achieving an error rate below 1% even when operands are much longer than those observed during training. We also compare the performance of learning agents receiving a different amount of explicit supervision, and we analyze the most common error patterns to better understand the limitations and biases resulting from our design choices.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 15 of its 21 references that are in the map. First posted on arXiv 17 Jan 2023.

Builds on

15 of 21 references.

References · 15

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  3. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,359
  4. 2019Analysing Mathematical Reasoning Abilities of Neural Modelscited by 331
  5. 2019Emergent Tool Use From Multi-Agent Autocurriculacited by 308
  6. 2017StarCraft II: A New Challenge for Reinforcement Learningcited by 268
  7. 2020A Closer Look at Invalid Action Masking in Policy Gradient Algorithmscited by 160
  8. 2015Neural GPUs Learn Algorithmscited by 118
  9. 2019Neural Execution of Graph Algorithmscited by 118
  10. 2021Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networkscited by 108
  11. 2017Building machines that adapt and compute like brainscited by 99
  12. 2018Reinforcement Learning of Theorem Provingcited by 69
3 more
  1. 2018Neural Arithmetic Logic Unitscited by 69
  2. 2020Neural Arithmetic Unitscited by 25
  3. 2022Transformers discover an elementary calculation system exploiting local attention and grid-like problem representationcited by 7

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Can neural networks do arithmetic? A survey on the elementary numerical skills of state-of-the-art deep learning modelscited by 18