Yuxing-Wang-THU/Surrogate-assisted-ERL

A Surrogate-Assisted Controller for Expensive Evolutionary Reinforcement Learning

28
/ 100
Experimental

This tool helps robotics researchers and engineers optimize the control policies for their robots more efficiently, especially when real-world testing is costly or time-consuming. It takes your existing hybrid reinforcement learning and evolutionary algorithm framework as input, and outputs a significantly faster and more stable optimization process for developing robot behaviors. It's designed for anyone working on continuous robot control tasks who faces high costs or long durations for environmental interactions.

No commits in the last 6 months.

Use this if you are developing control policies for robots using evolutionary reinforcement learning and find the process too slow or expensive due to the need for frequent interactions with the physical environment.

Not ideal if your robot control tasks are simple or inexpensive to simulate, or if you are not using hybrid reinforcement learning and evolutionary algorithms.

robotics-control evolutionary-robotics robot-learning continuous-control robot-simulation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

15

Forks

3

Language

Python

License

Last pushed

Jan 19, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Yuxing-Wang-THU/Surrogate-assisted-ERL"

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