Whiterrrrr/BREEZE
[NeurIPS 2025] The official implementation of "Towards Robust Zero-Shot Reinforcement Learning"
This project helps robotics researchers and practitioners efficiently train intelligent agents for complex control tasks. It takes pre-recorded behavioral datasets from general exploration and rapidly produces highly stable and effective control policies for specific, new tasks without needing additional task-specific training. Researchers working on robotic locomotion or goal-reaching could use this to accelerate policy development and improve agent performance.
Use this if you need to quickly adapt a robot or agent to perform a new task using existing data, aiming for robust performance and faster policy convergence than traditional methods.
Not ideal if you are looking for a tool for real-time, online learning where agents continuously interact with and learn from their environment.
Stars
14
Forks
3
Language
Python
License
MIT
Category
Last pushed
Jan 02, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Whiterrrrr/BREEZE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ZhengYinan-AIR/Diffusion-Planner
[ICLR 2025 Oral] The official implementation of "Diffusion-Based Planning for Autonomous Driving...
intuitive-robots/MoDE_Diffusion_Policy
[ICLR 25] Code for "Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers...
caio-freitas/GraphDiffusionImitate
Diffusion-based graph generative policies for imitation learning in robotics tasks 🧠🤖
LeCAR-Lab/model-based-diffusion
Official implementation for the paper "Model-based Diffusion for Trajectory Optimization"....
Weixy21/SafeDiffuser
Safe Planning with Diffusion Probabilistic Models