# DeepMind Lab2D

arXiv: https://arxiv.org/abs/2011.07027 · HTML: https://mlsanity.com/paper/2011.07027/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Nov 2020.

## Built on by (most cited first, 13 of 13)

- [Collaborating with Humans without Human Data](https://mlsanity.com/paper/2110.08176/) (2021)
- [Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot](https://mlsanity.com/paper/2107.06857/) (2021)
- [Quantifying the effects of environment and population diversity in multi-agent reinforcement learning](https://mlsanity.com/paper/2102.08370/) (2021)
- [FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2406.02081/) (2024)
- [Warmth and competence in human-agent cooperation](https://mlsanity.com/paper/2201.13448/) (2022)
- [SocialJax: An Evaluation Suite for Multi-agent Reinforcement Learning in Sequential Social Dilemmas](https://mlsanity.com/paper/2503.14576/) (2025)
- [Hidden Agenda: a Social Deduction Game with Diverse Learned Equilibria](https://mlsanity.com/paper/2201.01816/) (2022)
- [A multi-agent reinforcement learning model of reputation and cooperation in human groups](https://mlsanity.com/paper/2103.04982/) (2021)
- [Agent-Centric Representations for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2104.09402/) (2021)
- [Statistical discrimination in learning agents](https://mlsanity.com/paper/2110.11404/) (2021)
- [AMaze: An intuitive benchmark generator for fast prototyping of generalizable agents](https://mlsanity.com/paper/2411.13072/) (2024)
- [Reinforcement Learning: From Algorithms To Foundation Models](https://mlsanity.com/paper/2607.17560/) (2026)
- [Who Bears the Burden? Learning Responsibility for Shared Constraints in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2610.07491/) (2026)

## Abstract (arXiv)

We present DeepMind Lab2D, a scalable environment simulator for artificial intelligence research that facilitates researcher-led experimentation with environment design. DeepMind Lab2D was built with the specific needs of multi-agent deep reinforcement learning researchers in mind, but it may also be useful beyond that particular subfield.