zzbuzzard/boxjump

Box Jump is a co-operative multi-agent reinforcement learning environment!

34
/ 100
Emerging

This tool helps researchers and engineers design and test algorithms for agents that need to work together to achieve a common goal. It provides a simulation environment where multiple agents (boxes) must collaboratively stack themselves to build the tallest possible tower. You provide the control logic for each agent, and the system simulates their interactions and measures the tower height, allowing you to evaluate and refine your cooperative strategies.

No commits in the last 6 months.

Use this if you are developing or evaluating multi-agent reinforcement learning algorithms where agents need to coordinate to build a shared structure or achieve a collective height-based objective.

Not ideal if you are looking for a simulation environment for competitive multi-agent scenarios or tasks that don't involve physical construction or stacking.

multi-agent-systems cooperative-ai reinforcement-learning-environments robotics-simulation collaborative-task-training
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

13

Forks

2

Language

Python

License

MIT

Last pushed

Sep 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/zzbuzzard/boxjump"

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