Learning Program Synthesis for Integer Sequences from Scratch

02/24/2022
by   Thibault Gauthier, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/27/2023

Alien Coding

We introduce a self-learning algorithm for synthesizing programs for OEI...
research
04/06/2023

A Mathematical Benchmark for Inductive Theorem Provers

We present a benchmark of 29687 problems derived from the On-Line Encycl...
research
09/20/2022

FACT: Learning Governing Abstractions Behind Integer Sequences

Integer sequences are of central importance to the modeling of concepts ...
research
03/23/2022

Terms of Lucas sequences having a large smooth divisor

We show that the Kn–smooth part of a^n-1 for an integer a>1 is a^o(n) fo...
research
07/31/2018

Computing Integer Sequences: Filtering vs Generation (Functional Pearl)

As a report of a teaching experience, we analyse Haskell programs comput...
research
10/26/2021

On some combinatorial sequences associated to invariant theory

We study the enumerative and analytic properties of some sequences const...
research
02/09/2023

On Discovering Interesting Combinatorial Integer Sequences

We study the problem of generating interesting integer sequences with a ...

Please sign up or login with your details

Forgot password? Click here to reset