# DeepCrawl: Deep Reinforcement Learning for Turn-based Strategy Games

arXiv: https://arxiv.org/abs/2012.01914 · HTML: https://mlsanity.com/paper/2012.01914/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2020.

## Built on by (most cited first, 6 of 6)

- [Demonstration-efficient Inverse Reinforcement Learning in Procedurally Generated Environments](https://mlsanity.com/paper/2012.02527/) (2020)
- [Policy Fusion for Adaptive and Customizable Reinforcement Learning Agents](https://mlsanity.com/paper/2104.10610/) (2021)
- [Improving Generalization in Game Agents with Data Augmentation in Imitation Learning](https://mlsanity.com/paper/2309.12815/) (2023)
- [Efficient Reinforcement Learning via Decoupling Exploration and Utilization](https://mlsanity.com/paper/2312.15965/) (2023)
- [Human-Like Goalkeeping in a Realistic Football Simulation: a Sample-Efficient Reinforcement Learning Approach](https://mlsanity.com/paper/2510.23216/) (2025)
- [Augmenting Game AI with Deep Reinforcement Learning](https://mlsanity.com/paper/2606.20210/) (2026)

## Abstract (arXiv)

In this paper we introduce DeepCrawl, a fully-playable Roguelike prototype for iOS and Android in which all agents are controlled by policy networks trained using Deep Reinforcement Learning (DRL). Our aim is to understand whether recent advances in DRL can be used to develop convincing behavioral models for non-player characters in videogames. We begin with an analysis of requirements that such an AI system should satisfy in order to be practically applicable in video game development, and identify the elements of the DRL model used in the DeepCrawl prototype. The successes and limitations of DeepCrawl are documented through a series of playability tests performed on the final game. We believe that the techniques we propose offer insight into innovative new avenues for the development of behaviors for non-player characters in video games, as they offer the potential to overcome critical issues with