paper-with-me

홈 › Papers

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

2026-07-08 · Florian Fuchs, Jessy Gosselin-Grant, Boris Skuin, Michele Petteni, Alessandro Sestini, Joakim Bergdahl, Amir Baghi, Linus Gisslén arxiv

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.

📄 PDF Abstract BibTeX arXiv:2607.07498

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

From Prediction to Action: Critical Role of Performance Estimation for Machine-Learning-Driven Materials Discovery

2023-11-27 · Mario Boley, Felix Luong, Simon Teshuva, Daniel F Schmidt 외

Materials discovery driven by statistical property models is an iterative decision process, during which an initial data collection is extended with new data proposed by a model-informed acquisition function--with the go…

Gaussian Processes

TopiCLEAR: Adaptive embedding clustering for interpretable topic discovery from short texts

2025-12-07 · Aoi Fujita, Taichi Yamamoto, Yuri Nakayama, Ryota Kobayashi arxiv

Topic discovery is a fundamental technique for text mining that identifies abstract topics within large document collections. A recent approach to topic discovery is to cluster document or sentence embeddings, typically …

Scaling Unverifiable Rewards: A Case Study on Visual Insights

2025-12-27 · Shuyu Gan, James Mooney, Pan Hao, Renxiang Wang 외 arxiv

Large Language Model (LLM) agents can increasingly automate complex reasoning through Test-Time Scaling (TTS), iterative refinement guided by reward signals. However, many real-world tasks involve multi-stage pipeline wh…

Story Generation

Adaptive Multi-view Rule Discovery for Weakly-Supervised Compatible Products Prediction

2022-06-28 · Rongzhi Zhang, Rebecca West, Xiquan Cui, Chao Zhang

On e-commerce platforms, predicting if two products are compatible with each other is an important functionality to achieve trustworthy product recommendation and search experience for consumers. However, accurately pred…

AttributeLanguage ModelingLanguage ModellingProduct Recommendation

MADE: Benchmark Environments for Closed-Loop Materials Discovery

2026-01-28 · Shreshth A Malik, Tiarnan Doherty, Panagiotis Tigas, Muhammed Razzak 외 arxiv

Existing benchmarks for computational materials discovery primarily evaluate static predictive tasks or isolated computational sub-tasks. While valuable, these evaluations neglect the inherently iterative and adaptive na…

Decision Making