RLHF Courses and Certifications

RLHF for Finer Alignment with Gemma 3

Explore techniques developed in Gemma to mitigate reward hacking during RLHF, allowing for longer training and better alignment of language models with human preferences.

• YouTube
• 10 minutes
• Self-Paced
• Free Video

Yacine Mahdid

Exploring GRPO Through the RAFT Algorithm - RLHF and RLVR

Dive into GRPO's mechanics through RAFT algorithm analysis, comparing RLHF and RLVR paradigms from 2023-2025 studies to develop simplified reinforcement learning approaches for LLMs.

• YouTube
• 1 hour 4 minutes
• Self-Paced
• Free Video

Serrano.Academy

Reinforcement Learning for Large Language Models - RLHF, PPO, DPO, and GRPO

Discover how to fine-tune LLMs using RLHF, PPO, DPO, and GRPO techniques with practical deep reinforcement learning methods for transformer models.

• YouTube
• 2 hours 28 minutes
• Self-Paced
• Free Video

Generative AI Advanced Fine-Tuning for LLMs

138 ratings at Coursera

Fine-tune causal LLMs with instruction tuning, reward modeling, RLHF, PPO, and direct preference optimization, using Hugging Face trainers and LoRA in hands-on labs.

• Coursera
• 2 weeks, 5 hours a week
• Self-Paced
• Paid Course

Career Certificate

Quick Start Guide to Large Language Models (LLMs)

6 ratings at Coursera

Build and deploy LLMs at scale: fine-tune Llama 3 with RLHF, build Siamese BERT recommendation engines, GPT-4 retrieval systems, and vision transformer image captioning.

• Coursera
• 4 weeks, 5 hours a week
• Self-Paced
• Paid Course
• 3 courses

LLM Fine-Tuning and Customization Training

Fine-tune domain-specific LLMs with supervised methods, PEFT, and RLHF, handling data preparation, hyperparameter tuning, and evaluation, then tune Falcon-7B and build a LangChain plus DALL·E image app.

• Coursera
• 2 weeks, 2 hours a week
• Self-Paced
• Paid Course

Packt

Cutting-Edge Topics in Deep Reinforcement Learning

Explore advanced deep RL: continuous control with A2C, trust region methods (PPO, TRPO, ACKTR), black-box optimization, exploration strategies, RLHF, AlphaGo Zero, MuZero, and multi-agent learning.

• Coursera
• 8 weeks, 1 hour a week
• Self-Paced
• Paid Course

Data Science Courses

Deep Learning: RLHF, ChatGPT, and Alignment in LLMs - Lecture 14

Dive into advanced concepts of RLHF, ChatGPT training, and LLM alignment, exploring efficient transformers and the technical foundations behind modern language models.

• YouTube
• 1 hour 14 minutes
• Self-Paced
• Free Video

MLOps.community

Building and Curating Datasets for RLHF and LLM Fine-tuning

Learn effective strategies for dataset construction, curation, and annotation to enhance RLHF and LLM models using Argilla's open-source data platform for integrating human and machine feedback.

• YouTube
• 59 minutes
• Self-Paced
• Free Video

StatQuest with Josh Starmer

Reinforcement Learning with Human Feedback (RLHF), Clearly Explained

Discover how Reinforcement Learning with Human Feedback (RLHF) helps align language models like ChatGPT to generate polite, useful responses, with a clear explanation of pre-training, supervised fine-tuning, and reward model training.

• YouTube
• 18 minutes
• Self-Paced
• Free Video

Generative AI on AWS

Generative AI and Large Language Models: From GPT-3 to ChatGPT with RLHF

Explore the latest advancements in generative AI, from CodeWhisperer to ChatGPT, while learning about prompt engineering and reinforcement learning techniques for improved human-AI interaction.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

UofU Data Science

Reinforcement Learning from Human Feedback (RLHF) - Advances in Generative AI

Dive into reinforcement learning from human feedback (RLHF) and its crucial role in advancing generative AI systems, exploring key concepts, implementation strategies, and real-world applications.

• YouTube
• 1 hour 3 minutes
• Self-Paced
• Free Video

UofU Data Science

SFT Data and RLHF - Supervised Fine-Tuning and Reinforcement Learning from Human Feedback

Explore supervised fine-tuning data preparation and reinforcement learning from human feedback techniques for optimizing large language models in this technical deep dive.

• YouTube
• 1 hour 17 minutes
• Self-Paced
• Free Video

Mastering Generative AI: Advanced Fine-Tuning for LLMs

Build advanced, job-ready skills in fine-tuning using Hugging Face, reinforcement learning using proximal preference optimization (PPO), and optimal solutions for direct preference optimization (DPO).

• edX
• 2 weeks, 2-4 hours a week
• Self-Paced
• Free Online Course (Audit)

Andrej Karpathy

Deep Dive into Large Language Models: From ChatGPT to Training and Applications

Dive into a comprehensive exploration of Large Language Models, from fundamental concepts to advanced topics like RLHF, with insights from an industry expert on their development and practical applications.

• YouTube
• 3 hours 31 minutes
• Self-Paced
• Free Video