mlsanityData to 14 Oct 2026

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

arXiv 2607.07498 ↗First posted 8 Jul 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 23 references that are in the map. First posted on arXiv 8 Jul 2026.

Builds on

15 of 23 references.

References · 15

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2018Diversity is All You Need: Learning Skills without a Reward Functioncited by 752
  3. 2015Illuminating search spaces by mapping elitescited by 425
  4. 2016Successor Features for Transfer in Reinforcement Learningcited by 340
  5. 2019Emergent Tool Use From Multi-Agent Autocurriculacited by 313
  6. 2016Variational Intrinsic Controlcited by 267
  7. 2014Robots that can adapt like animalscited by 204
  8. 2019Discrete and Continuous Action Representation for Practical RL in Video Gamescited by 39
  9. 2021Augmenting Automated Game Testing with Deep Reinforcement Learningcited by 38
  10. 2022Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimalitycited by 37
  11. 2018Automated Playtesting with Procedural Personas through MCTS with Evolved Heuristicscited by 28
  12. 2021Improving Playtesting Coverage via Curiosity Driven Reinforcement Learning Agentscited by 28
3 more
  1. 2019Automated Video Game Testing Using Synthetic and Human-Like Agentscited by 22
  2. 2021Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigationcited by 17
  3. 2022Automated Play-Testing Through RL Based Human-Like Play-Styles Generationcited by 11

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning
  2. 2024Dominion: A New Frontier for AI Research
  3. 2024Learning to Play Air Hockey with Model-Based Deep Reinforcement Learning
  4. 2026CheatBench: Measuring Reward Gaming in AI Agents
  5. 2025Human-Like Goalkeeping in a Realistic Football Simulation: a Sample-Efficient Reinforcement Learning Approach
  6. 2026Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition
  7. 2021Markov Cricket: Using Forward and Inverse Reinforcement Learning to Model, Predict And Optimize Batting Performance in One-Day International Cricket
  8. 2026Beyond Scripted Search: Sample-Efficient Reward Discovery via Agentic Black-box Optimization