Uncertainty Aware Learning from Demonstrations in Multiple Contexts using Bayesian Neural Networks

13 Mar 2019Sanjay ThakurHerke van HoofJuan Camilo Gamboa HigueraDoina PrecupDavid Meger

Diversity of environments is a key challenge that causes learned robotic controllers to fail due to the discrepancies between the training and evaluation conditions. Training from demonstrations in various conditions can mitigate---but not completely prevent---such failures... (read more)

PDF Abstract

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper

🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet