Reward-Adaptive Iterative Discovery: A Case Study on Automated Game Testing for NHL26

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Florian Fuchs, Jessy Gosselin-Grant, Boris Skuin, Michele Petteni, Alessandro Sestini, Joakim Bergdahl, Amir Baghi, Linus Gisslén
• Venue: arXiv: cs.LG
• Published: 2026-07-08
• Collected: 2026-07-09
• URL: http://arxiv.org/abs/2607.07498v1
• PDF: https://arxiv.org/pdf/2607.07498v1
• DOI: UNKNOWN

Plain-Language Brief

The researchers present Reward-Adaptive Iterative Discovery (RAID), a new approach for automated game testing in the gaming industry, specifically focusing on the ice hockey game EA SPORTS NHL 26. The goal is to reduce the effort required for re-testing the goalie AI by training a population of goal scoring agents using Reinforcement Learning (RL). RAID aims to find multiple diverse high-quality solutions instead of overfitting to a single solution, as previous approaches often do.

What the Document Says

• The text discusses a new approach called Reward-Adaptive Iterative Discovery (RAID) for automated game testing in the gaming industry.
• The case study is based on EA SPORTS NHL 26, a development version of an ice hockey game.
• Human playtesters test the goalie AI for behavioral exploits in this game.
• RAID uses Reinforcement Learning (RL) to train a population of goal scoring agents to reduce re-testing effort after every game or behavior modification.
• The aim is to find multiple diverse high-quality solutions instead of overfitting to a single solution, as previous approaches often do.
• RAID was able to find six hockey scoring exploit strategies in a single experiment, which were qualitatively similar to those found through hours-long manual testing sessions.

Key Concepts Mentioned

• Automated game testing
• Reinforcement Learning (RL)
• EA SPORTS NHL 26
• Goalie AI exploits
• Human playtesters

Claims Made by the Document

• RAID reduces the effort of re-testing the goalie AI after every game or behavior modification.
• RAID finds multiple diverse high-quality solutions instead of overfitting to a single solution.

Evidence Used

• The text mentions the development version of EA SPORTS NHL 26 and human playtesters testing the goalie AI for behavioral exploits.
• The text explains that RAID uses Reinforcement Learning (RL) to train a population of goal scoring agents.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Testing is a major effort for the gaming industry, requiring a significant part of development budget and people power. We present a case study on a development version of the ice hockey game EA SPORTS NHL 26, for which human playtesters test the goalie AI for behavioral exploits. To reduce the effort of re-testing the goalie AI after every game or behavior modification in the development phase, we propose Reward-Adaptive Iterative Discovery (RAID), a novel approach to automatically find exploits using an iterative Reinforcement Learning (RL) approach that trains a population of goal scoring agents. While previous approaches can already successfully find exploits, RL algorithms tend to overfit to a single solution. We introduce a simple extension on top of existing RL algorithms, such that they find multiple diverse high-quality solutions. For our first deployment of this approach, within a single experiment we were able to find six hockey scoring exploit strategies that were qualitatively similar to those that playtesters had found in hours-long manual testing sessions.