Log In Sign Up

Deep Reinforcement Learning for Programming Language Correction

by   Rahul Gupta, et al.

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 29 tool, DeepFix, which uses a fully supervised neural machine translation approach.


page 1

page 2

page 3

page 4


Lolisa: Formal Syntax and Semantics for a Subset of the Solidity Programming Language

This article presents the formal syntax and semantics for a large subset...

Describing the syntax of programming languages using conjunctive and Boolean grammars

A classical result by Floyd ("On the non-existence of a phrase structure...

Merlin: A Language Server for OCaml (Experience Report)

We report on the experience of developing Merlin, a language server for ...

An Experiment with a User Manual of a Programming Language Based on a Denotational Semantics

Denotational models should provide an opportunity for the revision of cu...

Interpreted Programming Language Extension for 3D Render on the Web

There are tools to ease the 2D/3D graphics development for programmers. ...

A Practical Approach for Detecting Logical Error in Object Oriented Environment

A programming language is a formally constructed language designed to co...

Actions You Can Handle: Dependent Types for AI Plans

Verification of AI is a challenge that has engineering, algorithmic and ...