pathak22/modular-assemblies

[NeurIPS 2019] Code for the paper "Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity"

41
/ 100
Emerging

This project helps researchers and developers explore how to design and control complex, self-assembling robotic systems. It takes in specifications for modular "agent" parts and training parameters, then outputs policies for how these parts can combine and move to achieve tasks. This is ideal for robotics researchers, AI developers, and those working on adaptive systems or virtual creature design.

117 stars. No commits in the last 6 months.

Use this if you are researching how to create intelligent, adaptable systems from simple components that can dynamically assemble and coordinate to perform new functions without explicit pre-programming.

Not ideal if you need a plug-and-play solution for controlling an existing physical robot or a general-purpose reinforcement learning library without a focus on self-assembly.

robotics research adaptive systems artificial life multi-agent AI bio-inspired engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

117

Forks

16

Language

Python

License

Last pushed

Dec 13, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pathak22/modular-assemblies"

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