221 citations · 588 across the 17 of their papers we have counts for
Showing 2017Show all
2 papers · 1 filter
cs.RO2017★ 5 cited
Active Robotic Mapping through Deep Reinforcement Learning
Shane Barratt
We propose an approach to learning agents for active robotic mapping, where the goal is to map the environment as quickly as possible. The agent learns to map efficiently in simula…
stat.ML2017★ 17 cited
InterpNET: Neural Introspection for Interpretable Deep Learning
Shane Barratt
Humans are able to explain their reasoning. On the contrary, deep neural networks are not. This paper attempts to bridge this gap by introducing a new way to design interpretable n…