CHAI Members Publish New Papers
02 Sep 2021
CHAI members recently published the following papers in journals and conference venues.
ICML 2021
Smitha Milli, Luca Belli, and Moritz Hardt, Causal Inference Struggles with Agency on Online Platforms. ICML 2021
Kimin Lee, Michael Laskin, Aravind Srinivas, and Pieter Abbeel, SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning. ICML 2021 Spotlight paper
NeurIPS 2021
Kimin Lee, Laura Smith, Anca Dragan, and Pieter Abbeel, B-Pref: Benchmarking Preference-Based Reinforcement Learning. Accepted to NeurIPS 2021 Benchmark track
ICLR 2021
Adam Gleave, Michael Dennis, Shane Legg, Stuart Russell and Jan Leike, Quantifying Differences in Reward Functions. ICLR 2021
Cassidy Laidlaw, Sahil Singla, and Soheil Feizi, Perceptual Adversarial Robustness: Defense Against Unseen Threat Models. ICLR 2021
Other Venues
Smitha Milli, Luca Belli, and Moritz Hardt, From Optimizing Engagement to Measuring Value. FAccT 2021
Charlotte Roman, Michael Dennis, Andrew Critch, and Stuart Russell, Accumulating Risk Capital Through Investing in Cooperation. In Proc. AAMAS-21.
Dan Hendrycks, Kevin Zhao, Steven Basart, Jacob Steinhardt, and Dawn Song, Natural Adversarial Examples. CVPR 2021
Dan Hendrycks, Steven Basart, Norman Mu, Saurav Kadavath, Frank Wang, Evan Dorundo, Rahul Desai, Tyler Zhu, Samyak Parajuli, Mike Guo, Dawn Song, Jacob Steinhardt, and Justin Gilmer, The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization. ICCV 2021
Avik Jain, Lawrence Chan, Daniel S. Brown, and Anca D. Dragan, Optimal Cost Design for Model Predictive Control. Proceedings of the 3rd Conference on Learning for Dynamics and Control, PMLR 144:1205-1217, 2021
George Matheos, Alexander K. Lew, Matin Ghavamizadeh, Stuart Russell, Marco Cusumano-Towner, and Vikash K. Mansinghka, Transforming Worlds: Automated Involutive MCMC for Open-Universe Probabilistic Models. In Proc. 3rd Symposium on Advances in Approximate Bayesian Inference (AABI), 2021
Stuart Russell, Human-Compatible Artificial Intelligence. In Stephen Muggleton and Nick Chater (eds.), Human-Like Machine Intelligence, Oxford University Press, 2021