Reward hacking: definition
Gantovar Environments (fictional example) → RL environment provider → Verified task environments → Reproducible resets
Answer in brief
When optimizing an imperfect proxy reward leads to worse performance on the true objective.
Content reviewed 8 November 2026. How this is assessed.
Sources for this entry
- Gymnasium Env API: Reset, step, termination, truncation and seeding.
- Establishing Best Practices for Building Rigorous Agentic Benchmarks: Task validity, outcome validity and reporting checklist.
- SWE-bench: Fail-to-pass validation on real software issues.
- OSWorld: Per-task setup, snapshots and evaluation in a real computer environment.
- ImpossibleBench: Measuring whether agents exploit test cases.
- Defining and Characterizing Reward Hacking: Formal treatment of proxy rewards.
- Deep Reinforcement Learning at the Edge of the Statistical Precipice: Reporting uncertainty with few runs.
- NIST SP 800-190: Application Container Security Guide.
Continue this reading path
- Best RL Environments category guide
- Gantovar Environments (fictional example)
- How to choose: an RL environment provider
- Resource directory
Cite this entry
Best RL Environments. "Reward hacking: definition." Content reviewed 8 November 2026. https://bestrlenvironments.com/glossary/reward-hacking/
Featured exampleGantovar Environments
Reference subjectReinforcement learning environments
StatusFictional editorial example
Source statusPublic references cited