Christos Dimitrakakis
Research interests
Reinforcement learning
Differential privacy
Fairness
Bayesian inference and uncertainty
Current group members
Anne-Marie George (Oslo), Postdoctoral researcher on computational social choice under uncertainty.
Thomas Kleine Βüning (Oslo), PhD student on collaboration between humans and AI.
Meirav Segal (Oslo), PhD Student on fairness in AI.
Hannes Eriksson (Chalmers), PhD student on risk-sensitive reinforcement learning and autonomous vehicles.
Divya Grover (Chalmers), PhD student on reinforcement learning under information and computation constraints.
Emilio Jorge (Chalmers), PhD student on uncertainty in reinforcement learning .
Past members and collaborators
Debabrota Basu (INRIA), CR1. (Chalmers Postdoc 2018-2020) on reinforcement learning, differential privacy, adversarial ML.
Aristide Tossou (LG AI). *(Chalmers PhD 2015-2019) on Secure and Private Machine Learning and Decision Making.
David Parkes (Harvard), Professor.
Paul Tylkin (Harvard), PhD student (David Parkes).
Goran Radanovic (MPI SWS), Group Leader.
Yang Liu (UCSC), Professor.
Ronald Ortner (University of Leoben), Professor
Maryam Kamgarpour (ETHZ), Assistant Professor
Teaching
Decision Making Under Uncertainty and Reinforcement Learning (Neuchatel, Spring)
Advanced topics in Learning and Decision Making (Neuchatel, Spring)
Privacy and Security in AI (Neuchatel, Autumn)
Advanced topice in reproducibility, privacy and security (Neuchatel, Autumn)
Selected recent papers
SENTINEL: Taming Uncertainty with Ensemble-based Distributional Reinforcement Learning. To appear at UAI2022.
Interactive Inverse Reinforcement Learning for Cooperative Games, Cooperative-AI@NeurIPS 2021 (Best Paper Award). To appear at ICML2022.
Inferential Induction, I Cannot Believe It's Not Better@NeurIPS 2020
Epistemic Risk-Sensitive Reinforcement Learning, ESANN 2020
A Novel Individually Rational Objective In Multi-Agent Multi-Armed Bandit: Algorithms and Regret Bounds, AAMAS 2020
Bayesian Reinforcement Learning via Deep, Sparse Sampling, AISTATS 2020.
Bayesian fairness, AAAI 2019.
Multi-View Decision Processes, [poster] [video] [slides] NIPS 2017.
Calibrated fairness In bandits, FATML-17.
Differential privacy for Bayesian Inference through posterior sampling, JMLR, 2017.
Achieving privacy in the adversarial multi-armed bandit, AAAI 2017.