# Creating Pro-Level AI for a Real-Time Fighting Game Using Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/1904.03821 · HTML: https://mlsanity.com/paper/1904.03821/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2019.

## Built on by (most cited first, 14 of 14)

- [Artificial Intelligence for the Metaverse: A Survey](https://mlsanity.com/paper/2202.10336/) (2022)
- [A Comprehensive Review of Multi-Agent Reinforcement Learning in Video Games](https://mlsanity.com/paper/2509.03682/) (2025)
- [Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment](https://mlsanity.com/paper/2406.01103/) (2024)
- [Behaviour-Diverse Automatic Penetration Testing: A Curiosity-Driven Multi-Objective Deep Reinforcement Learning Approach](https://mlsanity.com/paper/2202.10630/) (2022)
- [Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models](https://mlsanity.com/paper/2508.21365/) (2025)
- [Decision Making in Monopoly using a Hybrid Deep Reinforcement Learning Approach](https://mlsanity.com/paper/2103.00683/) (2021)
- [Reinforcement Learning with a Terminator](https://mlsanity.com/paper/2205.15376/) (2022)
- [Lamarckian Platform: Pushing the Boundaries of Evolutionary Reinforcement Learning towards Asynchronous Commercial Games](https://mlsanity.com/paper/2209.10055/) (2022)
- [A Survey of Decision Making in Adversarial Games](https://mlsanity.com/paper/2207.07971/) (2022)
- [Diversity-based Deep Reinforcement Learning Towards Multidimensional Difficulty for Fighting Game AI](https://mlsanity.com/paper/2211.02759/) (2022)
- [Revisiting Experience Replayable Conditions](https://mlsanity.com/paper/2402.10374/) (2024)
- [Playing a 2D Game Indefinitely using NEAT and Reinforcement Learning](https://mlsanity.com/paper/2207.14140/) (2022)
- [Predicting Outcomes in Video Games with Long Short Term Memory Networks](https://mlsanity.com/paper/2402.15923/) (2024)
- [Game-Guided Skill Discovery through Self-Play for Playable Agent Control](https://mlsanity.com/paper/2609.40137/) (2026)

## Abstract (arXiv)

Reinforcement learning combined with deep neural networks has performed remarkably well in many genres of games recently. It has surpassed human-level performance in fixed game environments and turn-based two player board games. However, to the best of our knowledge, current research has yet to produce a result that has surpassed human-level performance in modern complex fighting games. This is due to the inherent difficulties with real-time fighting games, including: vast action spaces, action dependencies, and imperfect information. We overcame these challenges and made 1v1 battle AI agents for the commercial game "Blade & Soul". The trained agents competed against five professional gamers and achieved a win rate of 62%. This paper presents a practical reinforcement learning method that includes a novel self-play curriculum and data skipping techniques. Through the curriculum, three different styles of agents were created by reward shaping and were trained against each other. Additionally, this paper suggests data skipping techniques that could increase data efficiency and facilitate explorations in vast spaces. Since our method can be generally applied to all two-player competitive games with vast action spaces, we anticipate its application to game development including level design and automated balancing.