The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Teaching Large Language Models to Reason with Reinforcement Learning with Alex Havrilla - #680
Today we're joined by Alex Havrilla, a PhD student a...
more
Apr 16 2024 46m
Chapter 1 14 mins
Reinforcement Learning for Language ModelsChapter 2 10 mins
Exploring Model Output Diversity in RLChapter 3 7 mins
Comparison of RL Fine-Tuning AlgorithmsChapter 4 10 mins
Reasoning and Noise Impact in TrainingChapter 5 2 mins
Enhancing Transformer Model Generalization