# An Exploration of Collision-based Enemy Morphology Generation

arXiv: https://arxiv.org/abs/2606.02832 · HTML: https://mlsanity.com/paper/2606.02832/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 34 references that are in the map.
- First posted on arXiv 1 Jun 2026.

## Builds on (most cited first, 10 of 10)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [Unity: A General Platform for Intelligent Agents](https://mlsanity.com/paper/1809.02627/) (2018)
- [Reinforcement Learning for Improving Agent Design](https://mlsanity.com/paper/1810.03779/) (2018)
- [Procedural Content Generation in Games: A Survey with Insights on Emerging LLM Integration](https://mlsanity.com/paper/2410.15644/) (2024)
- [PCGRL+: Scaling, Control and Generalization in Reinforcement Learning Level Generators](https://mlsanity.com/paper/2408.12525/) (2024)
- [Automatic Game Design via Mechanic Generation](https://mlsanity.com/paper/1908.01420/) (2019)
- [Mechanic Maker 2.0: Reinforcement Learning for Evaluating Generated Rules](https://mlsanity.com/paper/2309.09476/) (2023)
- [Diversity-based Deep Reinforcement Learning Towards Multidimensional Difficulty for Fighting Game AI](https://mlsanity.com/paper/2211.02759/) (2022)
- [Mechanic Maker: Accessible Game Development Via Symbolic Learning Program Synthesis](https://mlsanity.com/paper/2410.01096/) (2024)

## Abstract (arXiv)

Despite a great deal of prior research into Procedural Content Generation (PCG), relatively little prior work has explored generating enemies for video games. In particular, there is almost no work on generating enemy morphologies, the basic body plan or collision information for in-game enemies, despite the existence of related morphology generation work in robotics. In this paper, we explore three different novel approaches to generate enemy morphologies based on player collision information. We found that each approach provides different strengths and weaknesses, but all had equivalent or better performance than an evolutionary baseline adapted from prior robotics morphology work.