# Diversity-based Deep Reinforcement Learning Towards Multidimensional Difficulty for Fighting Game AI

arXiv: https://arxiv.org/abs/2211.02759 · HTML: https://mlsanity.com/paper/2211.02759/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 28 references that are in the map.
- First posted on arXiv 4 Nov 2022.

## Builds on (most cited first, 11 of 11)

- [Diversity is All You Need: Learning Skills without a Reward Function](https://mlsanity.com/paper/1802.06070/) (2018)
- [Deep Reinforcement Learning: An Overview](https://mlsanity.com/paper/1701.07274/) (2017)
- [Variational Intrinsic Control](https://mlsanity.com/paper/1611.07507/) (2016)
- [Revisiting Fundamentals of Experience Replay](https://mlsanity.com/paper/2007.06700/) (2020)
- [Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning](https://mlsanity.com/paper/1712.06567/) (2017)
- [PCGRL: Procedural Content Generation via Reinforcement Learning](https://mlsanity.com/paper/2001.09212/) (2020)
- [Procedural Content Generation through Quality Diversity](https://mlsanity.com/paper/1907.04053/) (2019)
- [Automated Game Design via Conceptual Expansion](https://mlsanity.com/paper/1809.02232/) (2018)
- [Creating Pro-Level AI for a Real-Time Fighting Game Using Deep Reinforcement Learning](https://mlsanity.com/paper/1904.03821/) (2019)
- [Mixed-Initiative Level Design with RL Brush](https://mlsanity.com/paper/2008.02778/) (2020)
- [TaikoNation: Patterning-focused Chart Generation for Rhythm Action Games](https://mlsanity.com/paper/2107.12506/) (2021)

## Built on by (most cited first, 3 of 3)

- [Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment](https://mlsanity.com/paper/2406.01103/) (2024)
- [Measuring Diversity of Game Scenarios](https://mlsanity.com/paper/2404.15192/) (2024)
- [An Exploration of Collision-based Enemy Morphology Generation](https://mlsanity.com/paper/2606.02832/) (2026)

## Abstract (arXiv)

In fighting games, individual players of the same skill level often exhibit distinct strategies from one another through their gameplay. Despite this, the majority of AI agents for fighting games have only a single strategy for each "level" of difficulty. To make AI opponents more human-like, we'd ideally like to see multiple different strategies at each level of difficulty, a concept we refer to as "multidimensional" difficulty. In this paper, we introduce a diversity-based deep reinforcement learning approach for generating a set of agents of similar difficulty that utilize diverse strategies. We find this approach outperforms a baseline trained with specialized, human-authored reward functions in both diversity and performance.