zzbuzzard/boxjump
Box Jump is a co-operative multi-agent reinforcement learning environment!
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.
Stars
13
Forks
2
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
Toni-SM/skrl
Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with...
facebookresearch/BenchMARL
BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL...
utiasDSL/gym-pybullet-drones
PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
datamllab/rlcard
Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.
gtri/scrimmage
Multi-Agent Robotics Simulator