ZhengYinan-AIR/FISOR

[ICLR 2024] The official implementation of "Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model"

29
/ 100
Experimental

This project helps operations engineers and control system designers optimize complex systems while strictly adhering to safety rules. It takes historical operational data and existing safety constraints as input. The output is a refined control policy that not only improves performance but also guarantees safety, helping to prevent costly failures or hazardous situations.

120 stars. No commits in the last 6 months.

Use this if you need to develop safe, high-performing control policies for systems like autonomous vehicles, industrial robots, or data center cooling, using existing operational data without needing to interact with the real system during training.

Not ideal if your system lacks sufficient offline operational data, or if you need to explore and learn new behaviors through real-world interaction.

control-systems robotics process-optimization autonomous-driving industrial-automation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

120

Forks

9

Language

Python

License

Last pushed

Feb 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ZhengYinan-AIR/FISOR"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.