aweeraman/reinforcement-learning-continuous-control

Continuous Control with deep reinforcement learning where the agent must reach a moving ball with a double jointed arm

21
/ 100
Experimental

This project demonstrates how a robotic arm can learn to track and make contact with a moving ball through trial and error. It takes observations about the arm's position, rotation, and velocity, and outputs torques to apply to its joints. This tool is for researchers and developers exploring how to teach robotic systems complex, continuous movement tasks.

No commits in the last 6 months.

Use this if you are studying reinforcement learning for robotics or continuous control problems and need a practical example of an agent learning fine-tuned movements.

Not ideal if you need a solution for discrete control problems or are looking for a pre-built, ready-to-deploy robotic control system.

robotics motion-planning autonomous-systems machine-learning-research control-systems
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

9

Forks

1

Language

Python

License

Last pushed

Feb 10, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/aweeraman/reinforcement-learning-continuous-control"

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