# Deep Reinforcement Learning for Programming Language Correction

arXiv: https://arxiv.org/abs/1801.10467 · HTML: https://mlsanity.com/paper/1801.10467/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jan 2018.

## Built on by (most cited first, 4 of 4)

- [Break-It-Fix-It: Unsupervised Learning for Program Repair](https://mlsanity.com/paper/2106.06600/) (2021)
- [Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit](https://mlsanity.com/paper/2401.00288/) (2023)
- [SYNFIX: Automatically Fixing Syntax Errors using Compiler Diagnostics](https://mlsanity.com/paper/2104.14671/) (2021)
- [Variable Name Recovery in Decompiled Binary Code using Constrained Masked Language Modeling](https://mlsanity.com/paper/2103.12801/) (2021)

## Abstract (arXiv)

Novice programmers often struggle with the formal syntax of programming languages. To assist them, we design a novel programming language correction framework amenable to reinforcement learning. The framework allows an agent to mimic human actions for text navigation and editing. We demonstrate that the agent can be trained through self-exploration directly from the raw input, that is, program text itself, without any knowledge of the formal syntax of the programming language. We leverage expert demonstrations for one tenth of the training data to accelerate training. The proposed technique is evaluated on 6975 erroneous C programs with typographic errors, written by students during an introductory programming course. Our technique fixes 14% more programs and 29% more compiler error messages relative to those fixed by a state-of-the-art tool, DeepFix, which uses a fully supervised neural machine translation approach.