google-deepmind/lab2d
A customisable 2D platform for agent-based AI research
This tool helps AI researchers create customized 2D grid-based environments for testing machine learning agents. You define the world's layout using simple text maps and its rules with Lua code, then your AI agents interact with it. It's designed for researchers developing and evaluating new machine learning algorithms, providing a flexible simulation space.
439 stars. No commits in the last 6 months.
Use this if you are an AI researcher who needs to quickly design and implement various 2D grid-world simulations to train and test your machine learning agents.
Not ideal if you need a high-fidelity 3D simulation environment or if you are not comfortable with Lua scripting and defining environments through code.
Stars
439
Forks
59
Language
C++
License
Apache-2.0
Category
Last pushed
Oct 05, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/google-deepmind/lab2d"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
FutureAGI/Xenoverse
Benchmarking general decision-making with open & random worlds
helios-base/helios-base
HELIOS base is a sample implementation of the simulated soccer team for the RoboCup Soccer Simulation.
google-deepmind/lab
A customisable 3D platform for agent-based AI research
helios-base/librcsc
A base library to develop a simulated soccer team for the RoboCup Soccer Simulation
kohjingyu/search-agents
Code for the paper 🌳 Tree Search for Language Model Agents