RLHF Courses and Certifications

Oxen

Direct Preference Optimization (DPO) vs RLHF - Understanding Language Model Training

Delve into Direct Preference Optimization (DPO) and discover how it eliminates the need for separate reward models in language model training, offering a more efficient alternative to RLHF.

• YouTube
• 45 minutes
• On-Demand
• Free Video

MLOps.community

RLHF Data Collection in Practice - Part 2

Explore practical strategies for high-quality RLHF data collection, highlighting risks and effective techniques used in full-stack products to power ML teams.

• YouTube
• 12 minutes
• On-Demand
• Free Video

USENIX

Optimizing RLHF Training for Large Language Models with Stage Fusion

Discover RLHFuse, an efficient training system that optimizes RLHF for large language models through stage fusion, achieving up to 3.7× throughput improvement by addressing GPU utilization issues.

• YouTube
• 13 minutes
• On-Demand
• Free Video

UofU Data Science

Finetuning a Sequence-to-Sequence Model with RLHF

Master sequence-to-sequence model finetuning techniques and reinforcement learning from human feedback (RLHF) through hands-on demonstrations and practical implementations.

• YouTube
• 1 hour 20 minutes
• On-Demand
• Free Video

Shaw Talebi

Fine-tuning LLMs on Human Feedback (RLHF + DPO)

Explore fine-tuning techniques for LLMs using human feedback, comparing RLHF with the more efficient DPO method, including a practical example of fine-tuning Qwen on title preferences.

• YouTube
• 29 minutes
• On-Demand
• Free Video

Reinforcement Learning from Human Feedback (RLHF)

Learn how to make GenAI models truly reflect human values while gaining hands-on experience with advanced LLMs.

• DataCamp
• 4 hours
• On-Demand
• Free Trial Available

Donato Capitella

GPT, Instruction Fine-Tuning, and Reinforcement Learning from Human Feedback - Understanding ChatGPT's Foundation

Delve into the technical evolution of GPT models, exploring their architecture, instruction fine-tuning processes, and the role of RLHF in developing more capable language models.

• YouTube
• 18 minutes
• On-Demand
• Free Video

Intermediate ChatGPT

22 ratings at DataCamp

Learn the architecture behind GPT models and master advanced prompt crafting to unlock ChatGPT's full potential.

• DataCamp
• 1 hour
• On-Demand
• Free Trial Available

Reinforcement Learning in Python

Master the fundamentals of reinforcement learning (RL) to create models that can navigate complex real-world environments and train LLMs.

• DataCamp
• 12 hours
• On-Demand
• Free Trial Available

Reinforcement Learning from Human Feedback (RLHF) Explained

Explore RLHF's role in refining AI systems, focusing on components, benefits, and limitations. Learn how this technique aligns AI outputs with human values and preferences.

• YouTube
• 11 minutes
• On-Demand
• Free Video

Cooperative AI Foundation

RLHF: How to Learn from Human Feedback with Reinforcement Learning

Explore reinforcement learning techniques for incorporating human feedback in AI systems, enhancing multi-agent and human-AI interactions in social contexts.

• YouTube
• 59 minutes
• On-Demand
• Free Video

Generative AI on AWS

Generative AI and Large Language Models: Fine-tuning with SageMaker, PEFT, RLHF and PPO

Master advanced LLM fine-tuning techniques using Amazon SageMaker, exploring PEFT, RLHF, and PPO methodologies for optimized AI model performance and customization.

• YouTube
• 2 hours 32 minutes
• On-Demand
• Free Video

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
• On-Demand
• Free Video

Montreal Robotics

Robot Learning: Multi-Agent Reinforcement Learning and RLHF

Explore the foundations of multi-agent reinforcement learning (MARL) and its connection to reinforcement learning from human feedback (RLHF), including structured learning, algorithms, and training large language models.

• YouTube
• 1 hour 47 minutes
• On-Demand
• Free Video

Sundeep Saradhi Kanthety

Types of Fine Tuning in Generative AI - LoRA, PEFT, RLHF

Explore fine-tuning techniques in generative AI including full fine-tuning, LoRA, PEFT, adapter tuning, instruction fine-tuning, and reinforcement learning from human feedback.

• YouTube
• 17 minutes
• On-Demand
• Free Video