kyegomez/HLT
Implementation of the transformer from the paper: "Real-World Humanoid Locomotion with Reinforcement Learning"
This project helps robotics engineers and researchers working on advanced humanoid robots. It takes sensor observations (like video feeds) and high-level instructions as input. The output is a sequence of detailed actions for the robot to execute, enabling it to move realistically and adaptively in real-world environments.
Use this if you are developing reinforcement learning systems for humanoid robots and need a model that can process visual inputs and abstract commands to generate complex movement patterns.
Not ideal if you are working with non-humanoid robots or simpler control tasks that don't require advanced vision-to-action translation.
Stars
62
Forks
9
Language
Python
License
MIT
Category
Last pushed
Jan 31, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/kyegomez/HLT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lucidrains/x-transformers
A concise but complete full-attention transformer with a set of promising experimental features...
kanishkamisra/minicons
Utility for behavioral and representational analyses of Language Models
lucidrains/simple-hierarchical-transformer
Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT
lucidrains/dreamer4
Implementation of Danijar's latest iteration for his Dreamer line of work
Nicolepcx/Transformers-in-Action
This is the corresponding code for the book Transformers in Action