Proximal Policy Optimization (PPO) - How to train Large Language Models
Reinforcement Learning with Human Feedback (RLHF) is a method used for training Large Language Models (LLMs). In the heart of RLHF lies a very powerful reinforcement learning method called Proximal Policy Optimization. Learn about it in this simple video!
This is the first one in a series of 3 videos dedicated to the reinforcement learning methods used for training LLMs.
Full Playlist: https://www.youtube.com/playlist?list=PLs8w1Cdi-zvYviYYw_V3qe6SINReGF5M-
Video 0 (Optional): Introduction to deep reinforcement learning https://www.youtube.com/watch?v=SgC6AZss478
Video 1 (This one): Proximal Policy Optimization
Video 2: Reinforcement Learning with Human Feedback https://www.youtube.com/watch?v=Z_JUqJBpVOk
Video 3 (Coming soon!): Deterministic Policy Optimization
00:00 Introduction
01:25 Gridworld
03:10 States and Action
04:01 Values
07:30 Policy
09:39 Neural Networks
16:14 Training the value neural network (Gain)
22:50 Training the policy neural network (Surrogate Objective Function)
33:38 Clipping the surrogate objective function
36:49 Summary
Get the Grokking Machine Learning book!
https://manning.com/books/grokking-machine-learning
Discount code (40%): serranoyt
(Use the discount code on checkout)
Видео Proximal Policy Optimization (PPO) - How to train Large Language Models канала Serrano.Academy
This is the first one in a series of 3 videos dedicated to the reinforcement learning methods used for training LLMs.
Full Playlist: https://www.youtube.com/playlist?list=PLs8w1Cdi-zvYviYYw_V3qe6SINReGF5M-
Video 0 (Optional): Introduction to deep reinforcement learning https://www.youtube.com/watch?v=SgC6AZss478
Video 1 (This one): Proximal Policy Optimization
Video 2: Reinforcement Learning with Human Feedback https://www.youtube.com/watch?v=Z_JUqJBpVOk
Video 3 (Coming soon!): Deterministic Policy Optimization
00:00 Introduction
01:25 Gridworld
03:10 States and Action
04:01 Values
07:30 Policy
09:39 Neural Networks
16:14 Training the value neural network (Gain)
22:50 Training the policy neural network (Surrogate Objective Function)
33:38 Clipping the surrogate objective function
36:49 Summary
Get the Grokking Machine Learning book!
https://manning.com/books/grokking-machine-learning
Discount code (40%): serranoyt
(Use the discount code on checkout)
Видео Proximal Policy Optimization (PPO) - How to train Large Language Models канала Serrano.Academy
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Geometric series and my Irish heritageHow do you minimize a function when you can't take derivatives? CMA-ES and PSODecision trees - A friendly introductionReinforcement Learning with Human Feedback - How to train and fine-tune Transformer ModelsThe Binomial and Poisson DistributionsSingular Value Decomposition (SVD) and Image CompressionYou are much better at math than you thinkTraining Latent Dirichlet Allocation: Gibbs Sampling (Part 2 of 2)How Large Language Models are Shaping the FutureThe Attention Mechanism in Large Language ModelsThompson sampling, one armed bandits, and the Beta distributionBook by Luis Serrano - "Grokking Machine Learning" (40% off promo code)Latent Dirichlet Allocation (Part 1 of 2)The Gini Impurity Index explained in 8 minutes!Principal Component Analysis (PCA)Machine Learning: Testing and Error MetricsLogistic Regression and the Perceptron Algorithm: A friendly introductionClustering: K-means and HierarchicalWhat are Transformer Models and how do they work?A Friendly Introduction to Generative Adversarial Networks (GANs)