Planet Wars AI Challenge
Deadline: 2025-07-09
Webpage: https://github.com/SimonLucas/planet-wars-rts
Description
The competition is to evaluate agents to play variants of PlanetWars, a simple but challenging two player RTS game - the software used will be an updated version of this:
https://arxiv.org/pdf/1806.08544. (published at IEEE CIG Conference 2018)
The game software is available at https://github.com/SimonLucas/planet-wars-rts for participants to experiment with.
The competition ranking will be done on held-out maps, to avoid the AI agents specialising to particular maps.
We envisage running two versions: fully observable, and partially observable (with the latter a player cannot observe the number of ships on each enemy-occupied planet).
Entrants will submit entries by providing the GitHub URL and commit hash; our software then downloads the correct version and runs it in a docker image. Prior to the finals entrants will be able to see their ranking in the practice league.
Organizers
Simon is a full professor of AI in the School of Electronic Engineering and Computer Science at Queen Mary University of London where he leads the Game AI Research Group. He was previously Head of School of EECS at QMUL. He recently spent two years as a research scientist / software engineer in the Simulation-Based Testing team at Meta, applying simulation-based AI to automated testing.
Simon was the founding Editor-in-Chief of the IEEE Transactions on Games and co-founded the IEEE Conference on Games, was VP-Education for the IEEE Computational Intelligence Society and has served in many conference chair roles. His research is focused on simulation-based AI (e.g. Monte Carlo Graph Search, Rolling Horizon Evolution) and sample efficient optimisation.