NVlabs/DRAIL
[NeurIPS'24] The Official PyTorch implementation of DRAIL
DRAIL helps robotics and control engineers train agents for complex tasks like navigation, manipulation, and locomotion. It takes expert demonstration data and outputs a more effective control policy for your robot or agent. This is for researchers and practitioners working on training agents to perform tasks by observing expert examples.
No commits in the last 6 months.
Use this if you need to train a robot or agent to mimic human-like or expert behavior with greater precision and smoother control, especially when dealing with noisy or limited expert data.
Not ideal if you are looking for a method that learns solely through trial and error (reinforcement learning from scratch) rather than from expert demonstrations.
Stars
54
Forks
5
Language
Python
License
—
Category
Last pushed
Dec 03, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/NVlabs/DRAIL"
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