# MazeBase: A Sandbox for Learning from Games

arXiv: https://arxiv.org/abs/1511.07401 · HTML: https://mlsanity.com/paper/1511.07401/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2015.

## Built on by (most cited first, 4 of 4)

- [Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks](https://mlsanity.com/paper/2306.13831/) (2023)
- [Not All Memories are Created Equal: Learning to Forget by Expiring](https://mlsanity.com/paper/2105.06548/) (2021)
- [Mini-BEHAVIOR: A Procedurally Generated Benchmark for Long-horizon Decision-Making in Embodied AI](https://mlsanity.com/paper/2310.01824/) (2023)
- [CoGrid & the Multi-User Gymnasium: A Framework for Multi-Agent Experimentation](https://mlsanity.com/paper/2604.15044/) (2026)

## Abstract (arXiv)

This paper introduces MazeBase: an environment for simple 2D games, designed as a sandbox for machine learning approaches to reasoning and planning. Within it, we create 10 simple games embodying a range of algorithmic tasks (e.g. if-then statements or set negation). A variety of neural models (fully connected, convolutional network, memory network) are deployed via reinforcement learning on these games, with and without a procedurally generated curriculum. Despite the tasks' simplicity, the performance of the models is far from optimal, suggesting directions for future development. We also demonstrate the versatility of MazeBase by using it to emulate small combat scenarios from StarCraft. Models trained on the MazeBase version can be directly applied to StarCraft, where they consistently beat the in-game AI.