Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Christos Dimitrakakis

Fair Set Selection: Meritocracy and Social Welfare


Feb 23, 2021
Thomas Kleine Buening, Meirav Segal, Debabrota Basu, Christos Dimitrakakis


  Access Paper or Ask Questions

SENTINEL: Taming Uncertainty with Ensemble-based Distributional Reinforcement Learning


Feb 22, 2021
Hannes Eriksson, Debabrota Basu, Mina Alibeigi, Christos Dimitrakakis

* 17 pages, 6 figures 

  Access Paper or Ask Questions

Inferential Induction: Joint Bayesian Estimation of MDPs and Value Functions


Feb 08, 2020
Christos Dimitrakakis, Hannes Eriksson, Emilio Jorge, Divya Grover, Debabrota Basu

* 18 pages, 6 figures 

  Access Paper or Ask Questions

Near-optimal Bayesian Solution For Unknown Discrete Markov Decision Process


Jul 09, 2019
Aristide Tossou, Christos Dimitrakakis, Debabrota Basu

* Improved the text and added detailed proofs of claims Change title to better express the solution proposed 

  Access Paper or Ask Questions

Near-optimal Reinforcement Learning using Bayesian Quantiles


Jun 20, 2019
Aristide Tossou, Debabrota Basu, Christos Dimitrakakis

* arXiv admin note: substantial text overlap with arXiv:1905.12425 

  Access Paper or Ask Questions

Epistemic Risk-Sensitive Reinforcement Learning


Jun 14, 2019
Hannes Eriksson, Christos Dimitrakakis

* 8 pages, 2 figures 

  Access Paper or Ask Questions

Near-Optimal Online Egalitarian learning in General Sum Repeated Matrix Games


Jun 04, 2019
Aristide Tossou, Christos Dimitrakakis, Jaroslaw Rzepecki, Katja Hofmann


  Access Paper or Ask Questions

Differential Privacy for Multi-armed Bandits: What Is It and What Is Its Cost?


May 29, 2019
Debabrota Basu, Christos Dimitrakakis, Aristide Tossou

* 15 pages, 1 figure, 9 theorems 

  Access Paper or Ask Questions

Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities


May 27, 2019
Aristide Tossou, Debabrota Basu, Christos Dimitrakakis


  Access Paper or Ask Questions

Randomised Bayesian Least-Squares Policy Iteration


Apr 06, 2019
Nikolaos Tziortziotis, Christos Dimitrakakis, Michalis Vazirgiannis

* European Workshop on Reinforcement Learning 14, October 2018, Lille, France 

  Access Paper or Ask Questions

Deeper & Sparser Exploration


Feb 07, 2019
Divya Grover, Christos Dimitrakakis


  Access Paper or Ask Questions

Bayesian fairness


Nov 04, 2018
Christos Dimitrakakis, Yang Liu, David Parkes, Goran Radanovic

* 13 pages, 8 figures, to appear at AAAI 2019 

  Access Paper or Ask Questions

On The Differential Privacy of Thompson Sampling With Gaussian Prior


Jun 24, 2018
Aristide C. Y. Tossou, Christos Dimitrakakis

* Accepted in Privacy in Machine Learning and Artificial Intelligence Workshop 2018 

  Access Paper or Ask Questions

Nearly optimal exploration-exploitation decision thresholds


Jun 04, 2018
Christos Dimitrakakis

* 10 pages, 2 figures; IDIAP Research Report. Originally published in ICANN 2006. This version updates the paper with some links to previous and followup work 

  Access Paper or Ask Questions

Learning to Match


Jul 30, 2017
Philip Ekman, Sebastian Bellevik, Christos Dimitrakakis, Aristide Tossou

* 5 pages. This version will be presented at the VAMS Recsys workshop 2017 

  Access Paper or Ask Questions

Calibrated Fairness in Bandits


Jul 06, 2017
Yang Liu, Goran Radanovic, Christos Dimitrakakis, Debmalya Mandal, David C. Parkes

* To be presented at the FAT-ML'17 workshop 

  Access Paper or Ask Questions

Thompson Sampling For Stochastic Bandits with Graph Feedback


Jan 16, 2017
Aristide C. Y. Tossou, Christos Dimitrakakis, Devdatt Dubhashi


  Access Paper or Ask Questions

Achieving Privacy in the Adversarial Multi-Armed Bandit


Jan 16, 2017
Aristide C. Y. Tossou, Christos Dimitrakakis


  Access Paper or Ask Questions

Bayesian Differential Privacy through Posterior Sampling


Dec 23, 2016
Christos Dimitrakakis, Blaine Nelson, and Zuhe Zhang, Aikaterini Mitrokotsa, Benjamin Rubinstein

* 38 pages; An earlier version of this article was published in ALT 2014. This version has corrections and additional results 

  Access Paper or Ask Questions

On the Differential Privacy of Bayesian Inference


Dec 22, 2015
Zuhe Zhang, Benjamin Rubinstein, Christos Dimitrakakis

* AAAI 2016, Feb 2016, Phoenix, Arizona, United States 

  Access Paper or Ask Questions

Algorithms for Differentially Private Multi-Armed Bandits


Nov 27, 2015
Aristide Tossou, Christos Dimitrakakis

* AAAI 2016, Feb 2016, Phoenix, Arizona, United States 

  Access Paper or Ask Questions

Generalised Entropy MDPs and Minimax Regret


Dec 10, 2014
Emmanouil G. Androulakis, Christos Dimitrakakis

* 7 pages, NIPS workshop "From bad models to good policies" 

  Access Paper or Ask Questions

Personalized News Recommendation with Context Trees


Nov 03, 2014
Florent Garcin, Christos Dimitrakakis, Boi Faltings

* Proceedings of the 7th ACM conference on Recommender systems (2013), pp. 105--112 

  Access Paper or Ask Questions

Probabilistic inverse reinforcement learning in unknown environments


Aug 09, 2014
Aristide Tossou, Christos Dimitrakakis

* Appears in Proceedings of the Twenty-Ninth Conference on Uncertainty in Artificial Intelligence (UAI2013) 

  Access Paper or Ask Questions

Cover Tree Bayesian Reinforcement Learning


May 02, 2014
Nikolaos Tziortziotis, Christos Dimitrakakis, Konstantinos Blekas


  Access Paper or Ask Questions

ABC Reinforcement Learning


Jun 28, 2013
Christos Dimitrakakis, Nikolaos Tziortziotis

* Corrected version of paper appearing in ICML 2013 

  Access Paper or Ask Questions

Monte-Carlo utility estimates for Bayesian reinforcement learning


Mar 11, 2013
Christos Dimitrakakis

* 6 pages, 4 figures, 1 table, submitted to IEEE conference on decision and control 

  Access Paper or Ask Questions

Sparse Reward Processes


Sep 05, 2012
Christos Dimitrakakis

* 14 pages, 4 figures 

  Access Paper or Ask Questions

Bayesian multitask inverse reinforcement learning


Nov 17, 2011
Christos Dimitrakakis, Constantin Rothkopf

* Recent Advances in Reinforcement Learning LNCS 7188, pp. 273-284, 2012 
* Corrected version. 13 pages, 8 figures 

  Access Paper or Ask Questions