# Developing a Successful Bomberman Agent

arXiv: https://arxiv.org/abs/2203.09608 · HTML: https://mlsanity.com/paper/2203.09608/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 45 references that are in the map.
- First posted on arXiv 17 Mar 2022.

## Builds on (most cited first, 12 of 12)

- [Monte Carlo Tree Search: A Review of Recent Modifications and Applications](https://mlsanity.com/paper/2103.04931/) (2021)
- [General Video Game AI: a Multi-Track Framework for Evaluating Agents, Games and Content Generation Algorithms](https://mlsanity.com/paper/1802.10363/) (2018)
- [Pommerman: A Multi-Agent Playground](https://mlsanity.com/paper/1809.07124/) (2018)
- [Deep Multi-Agent Reinforcement Learning with Relevance Graphs](https://mlsanity.com/paper/1811.12557/) (2018)
- [Introducing the Hearthstone-AI Competition](https://mlsanity.com/paper/1906.04238/) (2019)
- [Rolling Horizon Evolutionary Algorithms for General Video Game Playing](https://mlsanity.com/paper/2003.12331/) (2020)
- [Skynet: A Top Deep RL Agent in the Inaugural Pommerman Team Competition](https://mlsanity.com/paper/1905.01360/) (2019)
- [Evolutionary Approach to Collectible Card Game Arena Deckbuilding using Active Genes](https://mlsanity.com/paper/2001.01326/) (2020)
- [Real-time tree search with pessimistic scenarios](https://mlsanity.com/paper/1902.10870/) (2019)
- [Rolling Horizon Coevolutionary Planning for Two-Player Video Games](https://mlsanity.com/paper/1607.01730/) (2016)
- [Continual Match Based Training in Pommerman: Technical Report](https://mlsanity.com/paper/1812.07297/) (2018)
- [TotalBotWar: A New Pseudo Real-time Multi-action Game Challenge and Competition for AI](https://mlsanity.com/paper/2009.08696/) (2020)

## Built on by (most cited first, 1 of 1)

- [Introducing Tales of Tribute AI Competition](https://mlsanity.com/paper/2305.08234/) (2023)

## Abstract (arXiv)

In this paper, we study AI approaches to successfully play a 2-4 players, full information, Bomberman variant published on the CodinGame platform. We compare the behavior of three search algorithms: Monte Carlo Tree Search, Rolling Horizon Evolution, and Beam Search. We present various enhancements leading to improve the agents' strength that concern search, opponent prediction, game state evaluation, and game engine encoding. Our top agent variant is based on a Beam Search with low-level bit-based state representation and evaluation function heavy relying on pruning unpromising states based on simulation-based estimation of survival. It reached the top one position among the 2,300 AI agents submitted on the CodinGame arena.