@article{interpretingreinforcementlearningagentsw, title = {Interpreting Reinforcement Learning Agents with Susceptibilities}, author = {Chris Elliott and Einar Urdshals and David Quarel and Daniel Murfet}, year = {2026}, eprint = {2605.08007}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.08007}, }