# Pommerman: A Multi-Agent Playground

arXiv: https://arxiv.org/abs/1809.07124 · HTML: https://mlsanity.com/paper/1809.07124/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Sep 2018.

## Built on by (most cited first, 30 of 30)

- [Building Cooperative Embodied Agents Modularly with Large Language Models](https://mlsanity.com/paper/2307.02485/) (2023)
- [Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots](https://mlsanity.com/paper/2310.13724/) (2023)
- [SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2212.07489/) (2022)
- [Embodied LLM Agents Learn to Cooperate in Organized Teams](https://mlsanity.com/paper/2403.12482/) (2024)
- [VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning](https://mlsanity.com/paper/2207.03530/) (2022)
- [A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents](https://mlsanity.com/paper/2601.12538/) (2026)
- [Any-Play: An Intrinsic Augmentation for Zero-Shot Coordination](https://mlsanity.com/paper/2201.12436/) (2022)
- [Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization](https://mlsanity.com/paper/2006.13258/) (2020)
- [MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning Library](https://mlsanity.com/paper/2210.13708/) (2022)
- [The Neural MMO Platform for Massively Multiagent Research](https://mlsanity.com/paper/2110.07594/) (2021)
- [Distributed Reinforcement Learning for Robot Teams: A Review](https://mlsanity.com/paper/2204.03516/) (2022)
- [Games for Artificial Intelligence Research: A Review and Perspectives](https://mlsanity.com/paper/2304.13269/) (2023)
- [MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2506.14990/) (2025)
- [Efficient Exploration in Resource-Restricted Reinforcement Learning](https://mlsanity.com/paper/2212.06988/) (2022)
- [Multi-Agent Advisor Q-Learning](https://mlsanity.com/paper/2111.00345/) (2021)
- [Self-Imitation Learning from Demonstrations](https://mlsanity.com/paper/2203.10905/) (2022)
- [Checkmating One, by Using Many: Combining Mixture of Experts with MCTS to Improve in Chess](https://mlsanity.com/paper/2401.16852/) (2024)
- [Multi-Agent Training for Pommerman: Curriculum Learning and Population-based Self-Play Approach](https://mlsanity.com/paper/2407.00662/) (2024)
- [Decision-making with Speculative Opponent Models](https://mlsanity.com/paper/2211.11940/) (2022)
- [Playing Against the Board: Rolling Horizon Evolutionary Algorithms Against Pandemic](https://mlsanity.com/paper/2103.15090/) (2021)
- [Developing a Successful Bomberman Agent](https://mlsanity.com/paper/2203.09608/) (2022)
- [Value-based CTDE Methods in Symmetric Two-team Markov Game: from Cooperation to Team Competition](https://mlsanity.com/paper/2211.11886/) (2022)
- [Toward Adaptable Multi-Agent Reinforcement Learning: An Assumption-Aware Review](https://mlsanity.com/paper/2507.10142/) (2025)
- [A Fast Evolutionary adaptation for MCTS in Pommerman](https://mlsanity.com/paper/2111.13770/) (2021)
- [Learning from Multiple Independent Advisors in Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2301.11153/) (2023)
- [Know your Enemy: Investigating Monte-Carlo Tree Search with Opponent Models in Pommerman](https://mlsanity.com/paper/2305.13206/) (2023)
- [The NeurIPS 2022 Neural MMO Challenge: A Massively Multiagent Competition with Specialization and Trade](https://mlsanity.com/paper/2311.03707/) (2023)
- [Effective Reward Specification in Deep Reinforcement Learning](https://mlsanity.com/paper/2412.07177/) (2024)
- [StarCraft+: Benchmarking Multi-agent Algorithms in Adversary Paradigm](https://mlsanity.com/paper/2512.16444/) (2025)
- [Reinforcement Learning: From Algorithms To Foundation Models](https://mlsanity.com/paper/2607.17560/) (2026)

## Abstract (arXiv)

We present Pommerman, a multi-agent environment based on the classic console game Bomberman. Pommerman consists of a set of scenarios, each having at least four players and containing both cooperative and competitive aspects. We believe that success in Pommerman will require a diverse set of tools and methods, including planning, opponent/teammate modeling, game theory, and communication, and consequently can serve well as a multi-agent benchmark. To date, we have already hosted one competition, and our next one will be featured in the NIPS 2018 competition track.