AI Governance Engineer
GitHub

Reward hacking

By Updated

A system finding an unintended way to maximise its reward or objective without doing what its designers meant 1. Answered by recording the objective and testing for unintended strategies, not only for the intended task.

Developed in
ch. 11, By learning paradigm
Chapters
ch. 11, AI Defined
Source
1 numbered reference, listed below

Where it is used

2 chapters of the Body of Knowledge use the term. Each link opens the first section that does.

Reward hacking: mentions per chapter3 mentions of the term across 2 of the 23 chapters of the Body of Knowledge; the chapters the glossary cross-references are drawn solid.Cross-referenced chapterOther chapter10 Reading List: 1 mention10 Reading List111 AI Defined: 2 mentions11 AI Defined2No mentions in the other 21 chaptersSource: the Body of Knowledgev0.5.0
Reward hacking: mentions per chapter3 mentions of the term across 2 of the 23 chapters of the Body of Knowledge; the chapters the glossary cross-references are drawn solid.Cross-referenced chapterOther chapter00010203040506070810 Reading List: 1 mention11011 AI Defined: 2 mentions211121314151617181920212223Source: the Body of Knowledge v0.5.0
Mentions per chapter How often each chapter names the term, with the chapters the glossary cross-references drawn solid. The longest bar is where to read the term in use; bars spread across many chapters mark a term that runs through the discipline.
Mentions as a table
Mentions of Reward hacking per chapter
ChapterMentionsCross-referenced
00 Preface0No
01 Definition0No
02 Why Now0No
03 Values & Principles0No
04 The Stack0No
05 Patterns0No
06 The Role0No
07 Maturity Model0No
08 Regulatory Map0No
10 Reading List1No
11 AI Defined2Yes
12 Governance Program0No
13 Risk Management0No
14 Development0No
15 Deployment0No
16 Fairness & XAI0No
17 Incidents0No
18 EU AI Act0No
19 Privacy & AI0No
20 Existing Law0No
21 AI Laws Worldwide0No
22 Principles & Standards0No
23 AI Agents0No
Reward hacking: related terms and patternsThe term at the centre; related terms on solid edges, the terms it is contrasted with on dashed edges, and the patterns that use it most in the colour of their layer.RelatedReward hackingRelated terms (6)Machine learning · RelatedMachine learningReinforcement learning from human feedback (RLHF) · RelatedRLHFReinforcement learning · RelatedReinforcement learningSelf-supervised learning · RelatedSelf-supervised learningSupervised learning · RelatedSupervised learningUnsupervised learning · RelatedUnsupervised learning
Reward hacking: related terms and patternsThe term at the centre; related terms on solid edges, the terms it is contrasted with on dashed edges, and the patterns that use it most in the colour of their layer.RelatedRelated terms (6)Machine learning · RelatedMachine learningReinforcement learning from human feedback (RLHF) · RelatedRLHFReinforcement learning · RelatedReinforcement learningSelf-supervised learning · RelatedSelf-supervised learningSupervised learning · RelatedSupervised learningUnsupervised learning · RelatedUnsupervised learningReward hacking
The term's neighbourhood Terms related to this one on solid edges, terms it is often confused with on dashed edges, and the patterns that use it most in the colour of their layer. Follow a dashed edge to check the distinction before you use either term.
Neighbourhood as a table
Neighbourhood of Reward hacking
FamilyItemRelation
Related termsMachine learningRelated
Related termsReinforcement learning from human feedback (RLHF)Related
Related termsReinforcement learningRelated
Related termsSelf-supervised learningRelated
Related termsSupervised learningRelated
Related termsUnsupervised learningRelated
  • Machine learning

    The branch of AI in which a system improves at a task by learning patterns from data rather than by following rules people wrote.

  • Reinforcement learning

    Learning to maximise a reward signal through trial and feedback.

  • Reinforcement learning from human feedback (RLHF)

    A way to align a pre-trained model: supervised fine-tuning on human demonstrations, then reinforcement learning against a reward model trained on human…

  • Self-supervised learning

    Learning by predicting parts of the input itself, such as the next token, over large corpora; the AI Act's definition of a general-purpose model names…

  • Supervised learning

    Learning from labelled examples.

  • Unsupervised learning

    Learning structure (clusters, anomalies) from data without labels.

Sources

  1. [1] Concrete Problems in AI Safety (reward hacking among five practical problems; arXiv 1606.06565). Amodei et al.. 2016-06-21. https://arxiv.org/abs/1606.06565 (verified: primary)

Definitions of legal terms paraphrase the cited text, which governs. Dated statements are as of .

Cite this term

García Aibar, J. (2026). Reward hacking. In AI Governance Engineering: The Thesis & Body of Knowledge (v0.5.0), Glossary. https://doi.org/10.5281/zenodo.22956197. https://aigovernanceengineer.com/glossary/reward-hacking. CC BY 4.0

BibTeX

@misc{aige2026rewardhacking,
  author  = {Jorge García Aibar},
  title   = {{Reward hacking}},
  note    = {Glossary, AI Governance Engineering: The Thesis \& Body of Knowledge, version 0.5.0},
  year    = {2026},
  doi     = {10.5281/zenodo.22956197},
  url     = {https://aigovernanceengineer.com/glossary/reward-hacking}
}