English

Learning Program Synthesis for Integer Sequences from Scratch

Artificial Intelligence 2022-11-30 v3 Symbolic Computation

Abstract

We present a self-learning approach for synthesizing programs from integer sequences. Our method relies on a tree search guided by a learned policy. Our system is tested on the On-Line Encyclopedia of Integer Sequences. There, it discovers, on its own, solutions for 27987 sequences starting from basic operators and without human-written training examples.

Keywords

Cite

@article{arxiv.2202.11908,
  title  = {Learning Program Synthesis for Integer Sequences from Scratch},
  author = {Thibault Gauthier and Josef Urban},
  journal= {arXiv preprint arXiv:2202.11908},
  year   = {2022}
}