https://github.com/vnadh/ai-vs.-human-text-classification-using-rl
This project uses Reinforcement Learning (RL) with Stable-Baselines3's PPO algorithm to classify text as either AI-generated or Human-written. The dataset consists of ~500K essays, labeled accordingly, and processed using TF-IDF vectorization. A custom Gymnasium environment is created to train the model to classify text based on rewards.
https://github.com/vnadh/ai-vs.-human-text-classification-using-rl
python3 sb3
Last synced: 7 months ago
JSON representation
This project uses Reinforcement Learning (RL) with Stable-Baselines3's PPO algorithm to classify text as either AI-generated or Human-written. The dataset consists of ~500K essays, labeled accordingly, and processed using TF-IDF vectorization. A custom Gymnasium environment is created to train the model to classify text based on rewards.
- Host: GitHub
- URL: https://github.com/vnadh/ai-vs.-human-text-classification-using-rl
- Owner: Vnadh
- Created: 2025-03-16T15:37:32.000Z (7 months ago)
- Default Branch: main
- Last Pushed: 2025-03-16T15:54:41.000Z (7 months ago)
- Last Synced: 2025-03-16T16:39:01.616Z (7 months ago)
- Topics: python3, sb3
- Language: Python
- Homepage: https://ai-vs-human-text-classification-using-rl-wq39ppmecofu7ut6z9ej9.streamlit.app/
- Size: 6.92 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0