2 code implementations • 10 Apr 2024 • Linas Nasvytis, Kai Sandbrink, Jakob Foerster, Tim Franzmeyer, Christian Schroeder de Witt
In this paper, we study the problem of out-of-distribution (OOD) detection in RL, which focuses on identifying situations at test time that RL agents have not encountered in their training environments.
Out-of-Distribution Detection Out of Distribution (OOD) Detection +2
no code implementations • 30 Nov 2022 • Linas Nasvytis
Following Gabaix and Laibson (2017), we first argue that time preference can be modelled as optimal Bayesian inference based on noisy signals about the future, so that it is affected by the perceived certainty of future outcomes.