Matthew E. Taylor

Improving Reinforcement Learning with Human Input

2018

Reinforcement learning (RL) has had many successes when learning autonomously. This paper and accompanying talk consider how to make use of a non-technical human participant, when available. In particular, we consider the case where a …

Work in Progress: Temporally Extended Auxiliary Tasks

2020 · arXiv (Cornell University)

Predictive auxiliary tasks have been shown to improve performance in numerous reinforcement learning works, however, this effect is still not well understood. The primary purpose of the work presented here is to investigate the impact …