For deep RL and the future of AI.

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

Playing Mario with Deep Reinforcement Learning

🍟 Vexo is a Hexo theme inspired by Vue's official website.

An advanced, set-and-forget automation tool for Microsoft Rewards. AutoRewarder performs Bing searches for PC and mobile point collection, collects Daily Sets, and uses mathematically driven, human-like input simulation (W3C Actions, Bezier curves, and smart scrolling). Packaged as an executable app for a seamless, plug-and-play experience

An amazing lottery app created for the world

jPasskit is an Java™ implementation of the Apple™ PassKit Web Service.

🤖 Automate Bing Searches 🔍, Quizzes 🧪, Polls 📝, & more for Bing Rewards. 💸

Ecency Mobile - reimagined social blogging, contribute and get rewarded (for Android and iOS)

对ChatGLM直接使用RLHF提升或降低目标输出概率|Modify ChatGLM output with only RLHF

💰 Warframe Drop Data in an easier to parse format.

👤 Multi-Armed Bandit Algorithms Library (MAB) 👮

This repository contains the code for SFT, RLHF, and DPO, designed for vision-based LLMs, including the LLaVA models and the LLaMA-3.2-vision models.

Scalable and extensible reinforcement learning for LM agents.

A free tool that let you farm twitch drops while sleeping

official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and Alternatives

The official CLI for the Lumen Protocol & Local Prompt Generation.

Auto-Rubric as Reward: From Implicit Preference to Explicit Generative Criteria

The primary development repository for the Bulwark project