Welcome to Bomberland
An open-source multi-agent AI competition inspired by Bomberman.
Program intelligent agents using strategies from tree search to deep reinforcement learning and compete to reach the top of the global leaderboard.
Try any strategy
A fun way to learn and experiment with the latest algorithms, from tree search to deep reinforcement learning.
Fully open-source
A fully customizable and open environment. Use it for research, learning, hosting your own competitions — and everything in between.
View on GitHubCommunity resources
Plenty of helpful resources to get you started with Bomberland. Get additional help by joining our 800+ member Discord community.
This is an introductory tutorial for anyone interested in building an agent for an AI programming competition or game. All you need to start is some familiarity with programming in Python.
Read more →
Tutorial mini-series on how to build a DL RL AI for Coder One's Bomberland competition using TensorFlow. In this part, we'll cover the deep learning specific Lingo, Making Replays, and converting them to TensorFlow Observations.
Read moreJoin the Bomberland competition
Start learning and competing using your skills in AI and machine learning. Submit your agents to the global leaderboard, play against other teams, and join our growing community.
