reddy-lab-code-research/PPOCoder
Code for the TMLR 2023 paper "PPOCoder: Execution-based Code Generation using Deep Reinforcement Learning"
This project helps software developers who want to automatically generate or translate code with higher accuracy. It takes an existing code generation model and fine-tunes it using feedback from code execution, like compiler errors and syntactic correctness. The output is a more robust code generation model that produces functional and syntactically correct code snippets or translations.
117 stars. No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher developing advanced code generation tools and need to improve the functional correctness and compilability of your generated code.
Not ideal if you are looking for an off-the-shelf application to generate code without any machine learning model fine-tuning or development experience.
Stars
117
Forks
13
Language
Python
License
MIT
Category
Last pushed
Jan 09, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ai-coding/reddy-lab-code-research/PPOCoder"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
k4black/codebleu
Pip compatible CodeBLEU metric implementation available for linux/macos/win
LiveCodeBench/LiveCodeBench
Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of...
EdinburghNLP/code-docstring-corpus
Preprocessed Python functions and docstrings for automated code documentation (code2doc) and...
hendrycks/apps
APPS: Automated Programming Progress Standard (NeurIPS 2021)
solis-team/Hydra
[FSE 2026] Do Not Treat Code as Natural Language: Implications for Repository-Level Code...