Reinforcement Learning should be better seen as a “fine-tuning” paradigm that can add capabilities to general-purpose foundation models, rather than a paradigm that can bootstrap intelligence from scratch.
Machine learning in concrete science: applications, challenges
5: GPT-3 Gets Better with RL, Hugging Face & Stable-baselines3, Meet Evolution Gym, Offline RL's Tailwinds, by Enes Bilgin, RL Agent
Deep Reinforcement Learning: Definition, Algorithms & Uses
RAG Vs Fine-Tuning for Enhancing LLM Performance - GeeksforGeeks
Fine-tuning 20B LLMs with RLHF on a 24GB consumer GPU
Google's Universal Pretraining Framework Unifies Language Learning
How Reinforcement Learning from AI Feedback works
Fine-tuning 20B LLMs with RLHF on a 24GB consumer GPU
AI, Free Full-Text
What is supervised fine-tuning? — Klu
25 Machine Learning Projects for All Levels