MazeBase: A Sandbox for Learning from Games

ArXiv PrePrint


This paper introduces an environment for simple 2D maze games, designed as a sandbox for machine learning approaches to reasoning and planning. Within it, we create 10 simple games based on algorithmic tasks (e.g. embodying simple if-then statements). We deploy a range of neural models (fully connected, convolutional network, memory network) on these games, with and without a procedurally generated curriculum. We show that these architectures can be trained with reinforcement to respectable performance on these tasks, but are still far from optimal, despite their simplicity. We also apply these models to games involving combat, including StarCraft, demonstrating their ability to learn non-trivial tactics which enable them to consistently beat the in-game AI.

Related Publications

All Publications

ICML - July 18, 2021

Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization

David Eriksson, Pierce I-Jen Chuang, Samuel Daulton, Peng Xia, Akshat Shrivastava, Arun Babu, Shicong Zhao, Ahmed Aly, Ganesh Venkatesh, Maximilian Balandat

ICML - July 18, 2021

Variational Auto-Regressive Gaussian Processes for Continual Learning

Sanyam Kapoor, Theofanis Karaletsos, Thang D. Bui

ICCV - October 11, 2021

Contrast and Classify: Training Robust VQA Models

Yash Kant, Abhinav Moudgil, Dhruv Batra, Devi Parikh, Harsh Agrawal

ICCV - October 10, 2021

Revitalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation

Taosha Fan, Kalyan Vasudev Alwala, Donglai Xiang, Weipeng Xu, Todd Murphey, Mustafa Mukadam

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy