Nevan Wichers

ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces

2020 · arXiv (Cornell University)

As mobile devices are becoming ubiquitous, regularly interacting with a variety of user interfaces (UIs) is a common aspect of daily life for many people. To improve the accessibility of these devices and to enable …

SAFER: Data-Efficient and Safe Reinforcement Learning via Skill Acquisition

2022 · arXiv (Cornell University)

Methods that extract policy primitives from offline demonstrations using deep generative models have shown promise at accelerating reinforcement learning(RL) for new tasks. Intuitively, these methods should also help to trainsafeRLagents because they enforce useful skills. …