Karim Abdel Sadek

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 be- havior 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 disam- biguating levels. We observe that the training signal from disambiguating levels could be amplified by regret-based prioritization. We formally show that approxi- mately 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.

ML-augmented algorithms utilize predictions to achieve performance beyond their worst-case bounds. Producing these predictions might be a costly operation – this motivated Im et al. (2022) to introduce the study of algorithms which use predictions parsimoniously. We design parsimonious algorithms for caching and MTS with action predictions, proposed by Antoniadis et al. (2023), focusing on the parameters of consistency (performance with perfect predictions) and smoothness (dependence of their performance on the prediction error). Our algorithm for caching is 1-consistent, robust, and its smoothness deteriorates with the decreasing number of available predictions. We propose an algorithm for general MTS whose consistency and smoothness both scale linearly with the decreasing number of predictions. Without the restriction on the number of available predictions, both algorithms match the earlier guarantees achieved by Antoniadis et al. (2023).