Mitigating Goal Misgeneralization via Minimax Regret
Keywords: Goal Misgeneralization, Unsupervised Environment Design, Reinforcement Learning, AI Safety, Alignment, Autocurricula
Abstract: Robustness research in reinforcement learning often focuses on ensuring that the policy consistently exhibits capable, goal-driven behavior. However, not every capable behavior is the intended behavior. *Goal misgeneralization* can occur when the policy generalizes capably with respect to a 'proxy goal' whose optimal behavior correlates with the intended goal on the training distribution, but not out of distribution. Though the intended goal would be ambiguous if they were perfectly correlated in training, we show progress can be made if the goals are only *nearly ambiguous*, with the training distribution containing a small proportion of *disambiguating* levels. We observe that the training signal from disambiguating levels could be amplified by regret-based prioritization. We formally show that approximately optimal policies on maximal-regret levels avoid the harmful effects of goal misgeneralization, which may exist without this prioritization. Empirically, we find that current regret-based Unsupervised Environment Design (UED) methods can mitigate the effects of goal misgeneralization, though do not always entirely eliminate it. Our theoretical and empirical results show that as UED methods improve they could further mitigate goal misgeneralization in practice.
Primary Area: alignment, fairness, safety, privacy, and societal considerations
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 12072
Loading