DropoutDAgger: A Bayesian Approach to Safe Imitation Learning

DropoutDAgger: A Bayesian Approach to Safe Imitation Learning

18 September 2017

Katherine Driggs-Campbell

Mykel J. Kochenderfer

Papers citing "DropoutDAgger: A Bayesian Approach to Safe Imitation Learning"

8 / 8 papers shown

Title
Agnostic Interactive Imitation Learning: New Theory and Practical Algorithms Yichen Li Chicheng Zhang OffRL 37 0 0 28 Dec 2023
Imitating careful experts to avoid catastrophic events J.R.P. Hanslope Laurence Aitchison OffRL 27 0 0 02 Feb 2023
DADAgger: Disagreement-Augmented Dataset Aggregation Akash Haridas Karim Hamadeh Samarendra Chandan Bindu Dash 17 0 0 03 Jan 2023
SARI: Shared Autonomy across Repeated Interaction Ananth Jonnavittula Shaunak A. Mehta Dylan P. Losey 40 10 0 19 May 2022
Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences Daniel S. Brown Russell Coleman R. Srinivasan S. Niekum BDL 30 101 0 21 Feb 2020
RadGrad: Active learning with loss gradients Paul Budnarain Renato Ferreira Pinto Junior Ilan Kogan 22 3 0 18 Jun 2019
Safe end-to-end imitation learning for model predictive control Keuntaek Lee Kamil Saigol Evangelos A. Theodorou BDL 24 24 0 27 Mar 2018
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning Y. Gal Zoubin Ghahramani UQCV BDL 287 9,156 0 06 Jun 2015