Smitha Milli
Smitha Milli
Verified email at berkeley.edu - Homepage
Title
Cited by
Cited by
Year
Inverse reward design
D Hadfield-Menell, S Milli, P Abbeel, SJ Russell, A Dragan
Advances in neural information processing systems, 6765-6774, 2017
1162017
The Social Cost of Strategic Classification
S Milli, J Miller, AD Dragan, M Hardt
FAT* 2019, 2019
402019
Model Reconstruction from Model Explanations
S Milli, L Schmidt, AD Dragan, M Hardt
FAT* 2019, 2019
312019
Should robots be obedient?
S Milli, D Hadfield-Menell, A Dragan, S Russell
IJCAI 2017, 2017
302017
Interpretable and pedagogical examples
S Milli, P Abbeel, I Mordatch
arXiv preprint arXiv:1711.00694, 2017
162017
Beyond canonical texts: A computational analysis of fanfiction
S Milli, D Bamman
Proceedings of the 2016 Conference on Empirical Methods in Natural Language …, 2016
152016
When does bounded-optimal metareasoning favor few cognitive systems?
S Milli, F Lieder, TL Griffiths
AAAI 2017, 4422-4428, 2017
102017
Strategic adaptation to classifiers: A causal perspective
J Miller, S Milli, M Hardt
arXiv preprint arXiv:1910.10362, 2019
82019
A rational reinterpretation of dual-process theories
S Milli, F Lieder, TL Griffiths
Preprint. doi, 2019
42019
Reward-rational (implicit) choice: A unifying formalism for reward learning
HJ Jeon, S Milli, AD Dragan
arXiv preprint arXiv:2002.04833, 2020
32020
Literal or Pedagogic Human? Analyzing Human Model Misspecification in Objective Learning
S Milli, AD Dragan
UAI 2019, 2019
32019
Value-laden Disciplinary Shifts in Machine Learning
R Dotan, S Milli
FAT* 2020, 2020
22020
Strategic Classification is Causal Modeling in Disguise
J Miller, S Milli, M Hardt
arXiv, arXiv: 1910.10362, 2019
22019
Augmenting course material with open access textbooks
S Milli, MA Hearst
Proceedings of the 11th Workshop on Innovative Use of NLP for Building …, 2016
22016
The system can't perform the operation now. Try again later.
Articles 1–14