Emma Tosch

Toybox: A Suite of Environments for Experimental Evaluation of Deep Reinforcement Learning

2019 · arXiv (Cornell University)

Evaluation of deep reinforcement learning (RL) is inherently challenging. In particular, learned policies are largely opaque, and hypotheses about the behavior of deep RL agents are difficult to test in black-box environments. Considerable effort has …

Exploring Consequences of Privacy Policies with Narrative Generation via Answer Set Programming

2022 · arXiv (Cornell University)

Informed consent has become increasingly salient for data privacy and its regulation. Entities from governments to for-profit companies have addressed concerns about data privacy with policies that enumerate the conditions for personal data storage and …