mihdalal/raps

[NeurIPS 2021] PyTorch Code for Accelerating Robotic Reinforcement Learning with Parameterized Action Primitives

39
/ 100
Emerging

This project helps roboticists and AI researchers accelerate the training of robot agents for complex tasks. By providing a framework that leverages pre-defined, high-level actions (primitives) instead of raw motor commands, it allows for quicker learning. Researchers input robot environment data and task definitions, and the output is a more efficiently trained robotic agent capable of performing intricate actions in environments like a kitchen or a manufacturing setup.

No commits in the last 6 months.

Use this if you are a roboticist or AI researcher developing reinforcement learning agents for robots and want to significantly speed up their learning process for complex, multi-step tasks.

Not ideal if you are working with very simple robot movements or if your robot's environment and tasks are highly unstructured and don't benefit from pre-defined action sequences.

robotics training reinforcement learning robot control AI for automation multi-task robotics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

79

Forks

11

Language

Python

License

MIT

Last pushed

Jul 11, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mihdalal/raps"

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