A
AI & Machine Learning
Artificial intelligence and machine learning content
Proximal Policy Optimization (PPO)
concept2 videos from 1 channel
Proximal Policy Optimization is a reinforcement learning algorithm used to train models by optimizing policies in a stable and efficient manner.
43:29Training a Unitree G1 to Walk w/ Reinforcement Learning
Using mjlab and PPO to train the Unitree G1 humanoid to walk inside and outside Neural Networks from Scratch book:…
3 months ago·sentdex
28:40Reinforcement learning with Unitree G1 humanoid - Dev w/ G1 P.5
Training and testing out an arm Policy for the Unitree G1 using the PPO algorithm. Github repo:…
8 months ago·sentdex