OSS Alternative - Discover Top Open Source Alternatives to Popular Software

opendilab/awesome-RLHF

A continually updated, curated list of essential resources for Reinforcement Learning with Human Feedback (RLHF), encompassing research papers, codebases, and datasets.

Core Features

Comprehensive collection of RLHF research papers categorized by year.

Includes links to relevant RLHF codebases and datasets.

Provides an overview and detailed explanation of RLHF concepts.

Covers RLHF applications in Large Language Models (LLMs) and video games.

Actively maintained to track the latest advancements in the RLHF field.

Detailed Introduction

This project serves as a central, continually updated repository for Reinforcement Learning with Human Feedback (RLHF) resources. It meticulously curates research papers, codebases, and datasets, offering a comprehensive overview of this critical AI domain. RLHF is pivotal for aligning AI models, particularly Large Language Models, with complex human values and intentions. By providing a structured collection, the project empowers researchers and practitioners to easily access and explore the frontier of RLHF, facilitating advancements in areas from natural language processing to game AI.