Imperfect World Models are Exploitable
Abstract
We propose a novel definition of model exploitation in reinforcement learning. Informally, a world model is exploitable if it implies that one policy should be strictly preferred over another while the environment's true transition model implies the reverse. We analogize our definition with a prior characterization of reward hacking but show that the associated proof of inevitability does not transfer to exploitation. To overcome this obstruction, we develop a general theory of reward hacking and model exploitation that proves that exploitation is essentially unavoidable on large policy sets and yields the corresponding claim for hacking as a special case. Unfortunately, we also find that the conditions that guarantee unhackability in finite policy sets have no counterpart that precludes exploitation. Consequently, we introduce a relaxed notion of exploitation and derive a safe horizon within which it can be avoided. Taken together, our results establish a formal bridge between reward hacking and model exploitation and elucidate the limits of safe planning in world models.
Cite
@article{arxiv.2605.15960,
title = {Imperfect World Models are Exploitable},
author = {Logan Mondal Bhamidipaty and Esmeralda S. Whitammer and David Abel and Mykel J. Kochenderfer and Subramanian Ramamoorthy},
journal= {arXiv preprint arXiv:2605.15960},
year = {2026}
}
Comments
17 pages, 3 figures, 2 tables; modified (fixed metadata)