Jonas Frey

TL;DR: This work proposes a cooperative adversarial method for obtaining single versatile policies with controllable skill sets from unlabeled datasets containing diverse state transition patterns by maximizing their discriminability.

TL;DR: This work proposes a generative adversarial method for inferring reward functions from partial and potentially physically incompatible demonstrations for successful skill acquirement where reference or expert demonstrations are not easily accessible.

TL;DR: In this article , the authors performed targeted photometry of period aliases to attempt to recover the true period of HIP 9618 b, and successfully determined its true period to be 52.56349 d.