Tom Gilbert Publishes “Subjectifying Objectivity”

20 Sep 2020

CHAI PhD candidate Thomas Krendl Gilbert and collaborator Andrew Loveridge published “Subjectifying Objectivity: Delineating Tastes in Theoretical Quantum Gravity Research” in Social Studies of Science. Below is the abstract of the paper:

IJCAI-20 Accepts Two Papers by CHAI PhD Student Rachel Freedman

10 Sep 2020

CHAI PhD student Rachel Freedman will present two papers at a workshop at IJCAI 2020. The first paper, “Choice Set Misspecification in Reward Inference,” is coauthored with CHAI Professor Anca Dragan and PhD student Rohin Shah. The paper analyzes what happens when a robot inferring reward functions from human feedback makes incorrect assumptions about the human’s choice set. The second paper, “Aligning with Heterogeneous Preferences for Kidney Exchange,” addresses the problem of preference aggregation by AI algorithms in a real-world public health context: kidney exchange. The paper suggests a roadmap for future automated moral decision making on behalf of heterogeneous groups.

IJCAI-20 Accepts Michael Wellman Paper

“Market Manipulation: An Adversarial Learning Framework for Detection and Evasion,” a new paper by University of Michigan Professor Michael Wellman and Xintong Wang, has been accepted by IJCAI-20. In the paper, they propose an adversarial learning framework to capture the evolving game between a regulator who develops tools to detect market manipulation and a manipulator who obfuscates actions to evade detection. Their experimental results demonstrate the possibility of automatically generating a diverse set of unseen manipulation strategies that can facilitate the training of more robust detection algorithms.

Stuart Russell’s Recent Media Appearances

Professor Stuart Russell gave several noteworthy presentations over the last few months.

Summer 2020 Interns

03 Sep 2020

This summer CHAI members virtually mentored eight interns. CHAI interns develop essential research skills in the fields of machine learning and AI safety, preparing them for graduate school and industry opportunities.
Cynthia Chen, an undergrad from University of Hong Kong, was mentored by Sam and Scott, and they were working on using tools in causality to assist ML with a focus on imitation learning.

Six New PhD Students Join CHAI

01 Sep 2020

Six new PhD students advised by CHAI Principal Investigators. We are thrilled to have these new PhD students join us!
The incoming students are Yuxi Liu, Micah Carroll, Cassidy Laidlaw, Alex Gunning, Alyssa Dayan, and Jessy Lin.

Five New Affiliates Join CHAI

20 Aug 2020

CHAI added five new affiliate members: Rediet Abebe, Niko Kolodny, Nika Haghtalab, Brian Christian, and Vincent Corruble. Welcome!

Thomas Gilbert Receives Inaugural Simons Institute Law and Society Fellowship

07 Aug 2020

Thomas Krendl Gilbert has been awarded the Simons Institute Law and Society Fellowship for its upcoming research program on Theory of Reinforcement Learning (Fall 2020).

Joseph Halpern and Xinming Liu Publish “Bounded Rationality in Las Vegas: Probabilistic Finite Automata PlayMulti-Armed Bandits”

03 Aug 2020

Joseph Halpern, CHAI PI and Professor at Cornell University, and Xinming Liu published their paper at Uncertainty in AI (UAI)’s Virtual Conference which was held August 3rd to 6th.

CHAI PhD Students Accept Positions at MIT, Princeton, and DeepMind

15 Jul 2020

Rohin Shah, Jaime Fernández Fisac, and Dylan Hadfield-Menell have accepted jobs to begin after the completion of their PhD studies.