Prospective Learning: Back to the Future
January 2022
Keyframe-focused visual imitation learning
Identifying and upsampling important frames from demonstration data can significantly boost imitation learning from histories, and scales easily to complex settings such as autonomous driving from vision.
July 2021
Fighting Copycat Agents in Behavioral Cloning from Observation Histories
December 2020
Causal Confusion in Imitation Learning
"Causal confusion", where spurious correlates are mistaken to be causes of expert actions, is commonly prevalent in imitation learning, leading to counterintuitive results where additional information can lead to worse task performance. How might one address this?
December 2019