Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis

2018-05-11 · ICLR 2018 1 · Rudy Bunel, Matthew Hausknecht, Jacob Devlin, Rishabh Singh, Pushmeet Kohli

Program synthesis is the task of automatically generating a program consistent with a specification. Recent years have seen proposal of a number of neural approaches for program synthesis, many of which adopt a sequence generation paradigm similar to neural machine translation, in which sequence-to-sequence models are trained to maximize the likelihood of known reference programs. While achieving impressive results, this strategy has two key limitations. First, it ignores Program Aliasing: the fact that many different programs may satisfy a given specification (especially with incomplete specifications such as a few input-output examples). By maximizing the likelihood of only a single reference program, it penalizes many semantically correct programs, which can adversely affect the synthesizer performance. Second, this strategy overlooks the fact that programs have a strict syntax that can be efficiently checked. To address the first limitation, we perform reinforcement learning on top of a supervised model with an objective that explicitly maximizes the likelihood of generating semantically correct programs. For addressing the second limitation, we introduce a training procedure that directly maximizes the probability of generating syntactically correct programs that fulfill the specification. We show that our contributions lead to improved accuracy of the models, especially in cases where the training data is limited.

📄 PDF Abstract BibTeX arXiv:1805.04276

Code (0)

등록된 구현이 없습니다.

Tasks

Machine Translation Program Synthesis reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Learning a Meta-Solver for Syntax-Guided Program Synthesis

2019-05-01 · ICLR 2019 5 · Xujie Si, Yuan Yang, Hanjun Dai, Mayur Naik 외

We study a general formulation of program synthesis called syntax-guided synthesis(SyGuS) that concerns synthesizing a program that follows a given grammar and satisfies a given logical specification. Both the logical sp…

Graph Neural Network Meta-Learning Program Synthesis Reinforcement Learning

Unsupervised Program Synthesis for Images By Sampling Without Replacement

2020-01-27 · Chenghui Zhou, Chun-Liang Li, Barnabas Poczos

Program synthesis has emerged as a successful approach to the image parsing task. Most prior works rely on a two-step scheme involving supervised pretraining of a Seq2Seq model with synthetic programs followed by reinfor…

Program Synthesis Reinforcement Learning (RL)

Code Building Genetic Programming

2020-08-09 · Edward Pantridge, Lee Spector

In recent years the field of genetic programming has made significant advances towards automatic programming. Research and development of contemporary program synthesis methods, such as PushGP and Grammar Guided Genetic …

Program Synthesis

HOTGP -- Higher-Order Typed Genetic Programming

2023-04-06 · Matheus Campos Fernandes, Fabrício Olivetti de França, Emilio Francesquini

Program synthesis is the process of generating a computer program following a set of specifications, which can be a high-level description of the problem and/or a set of input-output examples. The synthesis can be modele…

Program Synthesis valid

Program Synthesis as Dependency Quantified Formula Modulo Theory

2021-05-19 · Priyanka Golia, Subhajit Roy, Kuldeep S. Meel

Given a specification $\varphi(X,Y)$ over inputs $X$ and output $Y$, defined over a background theory $\mathbb{T}$, the problem of program synthesis is to design a program $f$ such that $Y=f(X)$ satisfies the specificati…