Craftium: Bridging Flexibility and Efficiency for Rich 3D Single- and Multi-Agent Environments

Mikel Malagón, Josu Ceberio, Jose A. Lozano
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42765-42794, 2025.

Abstract

Advances in large models, reinforcement learning, and open-endedness have accelerated progress toward autonomous agents that can learn and interact in the real world. To achieve this, flexible tools are needed to create rich, yet computationally efficient, environments. While scalable 2D environments fail to address key real-world challenges like 3D navigation and spatial reasoning, more complex 3D environments are computationally expensive and lack features like customizability and multi-agent support. This paper introduces Craftium, a highly customizable and easy-to-use platform for building rich 3D single- and multi-agent environments. We showcase environments of different complexity and nature: from single- and multi-agent tasks to vast worlds with many creatures and biomes, and customizable procedural task generators. Benchmarking shows that Craftium significantly reduces the computational cost of alternatives of similar richness, achieving +2K steps per second more than Minecraft-based frameworks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-malagon25a, title = {Craftium: Bridging Flexibility and Efficiency for Rich 3{D} Single- and Multi-Agent Environments}, author = {Malag\'{o}n, Mikel and Ceberio, Josu and Lozano, Jose A.}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {42765--42794}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/malagon25a/malagon25a.pdf}, url = {https://proceedings.mlr.press/v267/malagon25a.html}, abstract = {Advances in large models, reinforcement learning, and open-endedness have accelerated progress toward autonomous agents that can learn and interact in the real world. To achieve this, flexible tools are needed to create rich, yet computationally efficient, environments. While scalable 2D environments fail to address key real-world challenges like 3D navigation and spatial reasoning, more complex 3D environments are computationally expensive and lack features like customizability and multi-agent support. This paper introduces Craftium, a highly customizable and easy-to-use platform for building rich 3D single- and multi-agent environments. We showcase environments of different complexity and nature: from single- and multi-agent tasks to vast worlds with many creatures and biomes, and customizable procedural task generators. Benchmarking shows that Craftium significantly reduces the computational cost of alternatives of similar richness, achieving +2K steps per second more than Minecraft-based frameworks.} }
Endnote
%0 Conference Paper %T Craftium: Bridging Flexibility and Efficiency for Rich 3D Single- and Multi-Agent Environments %A Mikel Malagón %A Josu Ceberio %A Jose A. Lozano %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-malagon25a %I PMLR %P 42765--42794 %U https://proceedings.mlr.press/v267/malagon25a.html %V 267 %X Advances in large models, reinforcement learning, and open-endedness have accelerated progress toward autonomous agents that can learn and interact in the real world. To achieve this, flexible tools are needed to create rich, yet computationally efficient, environments. While scalable 2D environments fail to address key real-world challenges like 3D navigation and spatial reasoning, more complex 3D environments are computationally expensive and lack features like customizability and multi-agent support. This paper introduces Craftium, a highly customizable and easy-to-use platform for building rich 3D single- and multi-agent environments. We showcase environments of different complexity and nature: from single- and multi-agent tasks to vast worlds with many creatures and biomes, and customizable procedural task generators. Benchmarking shows that Craftium significantly reduces the computational cost of alternatives of similar richness, achieving +2K steps per second more than Minecraft-based frameworks.
APA
Malagón, M., Ceberio, J. & Lozano, J.A.. (2025). Craftium: Bridging Flexibility and Efficiency for Rich 3D Single- and Multi-Agent Environments. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:42765-42794 Available from https://proceedings.mlr.press/v267/malagon25a.html.

Related Material