Thore Graepel

Microsoft Research

Smooth markets: A basic mechanism for organizing gradient-based learners

Jan 18, 2020
David Balduzzi, Wojciech M Czarnecki, Thomas W Anthony, Ian M Gemp, Edward Hughes, Joel Z Leibo, Georgios Piliouras, Thore Graepel

* ICLR 2020 
* 18 pages, 3 figures 

  Access Model/Code and Paper
Biases for Emergent Communication in Multi-agent Reinforcement Learning

Dec 11, 2019
Tom Eccles, Yoram Bachrach, Guy Lever, Angeliki Lazaridou, Thore Graepel

* Accepted at NeurIPS 2019 

  Access Model/Code and Paper
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model

Nov 19, 2019
Julian Schrittwieser, Ioannis Antonoglou, Thomas Hubert, Karen Simonyan, Laurent Sifre, Simon Schmitt, Arthur Guez, Edward Lockhart, Demis Hassabis, Thore Graepel, Timothy Lillicrap, David Silver

  Access Model/Code and Paper
A Generalized Training Approach for Multiagent Learning

Sep 27, 2019
Paul Muller, Shayegan Omidshafiei, Mark Rowland, Karl Tuyls, Julien Perolat, Siqi Liu, Daniel Hennes, Luke Marris, Marc Lanctot, Edward Hughes, Zhe Wang, Guy Lever, Nicolas Heess, Thore Graepel, Remi Munos

  Access Model/Code and Paper
A Neural Architecture for Designing Truthful and Efficient Auctions

Jul 11, 2019
Andrea Tacchetti, DJ Strouse, Marta Garnelo, Thore Graepel, Yoram Bachrach

  Access Model/Code and Paper
Differentiable Game Mechanics

May 13, 2019
Alistair Letcher, David Balduzzi, Sebastien Racaniere, James Martens, Jakob Foerster, Karl Tuyls, Thore Graepel

* Journal of Machine Learning Research (JMLR), v20 (84) 1-40, 2019 
* JMLR 2019, journal version of arXiv:1802.05642 

  Access Model/Code and Paper
Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Research

Mar 11, 2019
Joel Z. Leibo, Edward Hughes, Marc Lanctot, Thore Graepel

* 16 pages, 2 figures 

  Access Model/Code and Paper
Emergent Coordination Through Competition

Feb 21, 2019
Siqi Liu, Guy Lever, Josh Merel, Saran Tunyasuvunakool, Nicolas Heess, Thore Graepel

  Access Model/Code and Paper
Open-ended Learning in Symmetric Zero-sum Games

Jan 23, 2019
David Balduzzi, Marta Garnelo, Yoram Bachrach, Wojciech M. Czarnecki, Julien Perolat, Max Jaderberg, Thore Graepel

* 18 pages, 7 figures 

  Access Model/Code and Paper
Malthusian Reinforcement Learning

Dec 17, 2018
Joel Z. Leibo, Julien Perolat, Edward Hughes, Steven Wheelwright, Adam H. Marblestone, Edgar Duéñez-Guzmán, Peter Sunehag, Iain Dunning, Thore Graepel

* 9 pages, 2 tables, 4 figures 

  Access Model/Code and Paper
Re-evaluating Evaluation

Oct 30, 2018
David Balduzzi, Karl Tuyls, Julien Perolat, Thore Graepel

* NIPS 2018, final version 

  Access Model/Code and Paper
Relational Forward Models for Multi-Agent Learning

Sep 28, 2018
Andrea Tacchetti, H. Francis Song, Pedro A. M. Mediano, Vinicius Zambaldi, Neil C. Rabinowitz, Thore Graepel, Matthew Botvinick, Peter W. Battaglia

  Access Model/Code and Paper
Inequity aversion improves cooperation in intertemporal social dilemmas

Sep 27, 2018
Edward Hughes, Joel Z. Leibo, Matthew G. Phillips, Karl Tuyls, Edgar A. Duéñez-Guzmán, Antonio García Castañeda, Iain Dunning, Tina Zhu, Kevin R. McKee, Raphael Koster, Heather Roff, Thore Graepel

* 15 pages, 8 figures 

  Access Model/Code and Paper
Human-level performance in first-person multiplayer games with population-based deep reinforcement learning

Jul 03, 2018
Max Jaderberg, Wojciech M. Czarnecki, Iain Dunning, Luke Marris, Guy Lever, Antonio Garcia Castaneda, Charles Beattie, Neil C. Rabinowitz, Ari S. Morcos, Avraham Ruderman, Nicolas Sonnerat, Tim Green, Louise Deason, Joel Z. Leibo, David Silver, Demis Hassabis, Koray Kavukcuoglu, Thore Graepel

  Access Model/Code and Paper
Adaptive Mechanism Design: Learning to Promote Cooperation

Jun 11, 2018
Tobias Baumann, Thore Graepel, John Shawe-Taylor

  Access Model/Code and Paper
The Mechanics of n-Player Differentiable Games

Jun 06, 2018
David Balduzzi, Sebastien Racaniere, James Martens, Jakob Foerster, Karl Tuyls, Thore Graepel

* PMLR volume 80, 2018 
* ICML 2018, final version 

  Access Model/Code and Paper
Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

Dec 05, 2017
David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, Timothy Lillicrap, Karen Simonyan, Demis Hassabis

  Access Model/Code and Paper
A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning

Nov 07, 2017
Marc Lanctot, Vinicius Zambaldi, Audrunas Gruslys, Angeliki Lazaridou, Karl Tuyls, Julien Perolat, David Silver, Thore Graepel

* Camera-ready copy of NIPS 2017 paper, including appendix 

  Access Model/Code and Paper
A multi-agent reinforcement learning model of common-pool resource appropriation

Sep 06, 2017
Julien Perolat, Joel Z. Leibo, Vinicius Zambaldi, Charles Beattie, Karl Tuyls, Thore Graepel

* 15 pages, 11 figures 

  Access Model/Code and Paper
Value-Decomposition Networks For Cooperative Multi-Agent Learning

Jun 16, 2017
Peter Sunehag, Guy Lever, Audrunas Gruslys, Wojciech Marian Czarnecki, Vinicius Zambaldi, Max Jaderberg, Marc Lanctot, Nicolas Sonnerat, Joel Z. Leibo, Karl Tuyls, Thore Graepel

  Access Model/Code and Paper
Learning Shared Representations in Multi-task Reinforcement Learning

Mar 07, 2016
Diana Borsa, Thore Graepel, John Shawe-Taylor

  Access Model/Code and Paper
The Wreath Process: A totally generative model of geometric shape based on nested symmetries

Jun 09, 2015
Diana Borsa, Thore Graepel, Andrew Gordon

* 10 pages(double-column), 60+ figures 

  Access Model/Code and Paper
A Comparison of learning algorithms on the Arcade Learning Environment

Oct 31, 2014
Aaron Defazio, Thore Graepel

  Access Model/Code and Paper
Compiling Relational Database Schemata into Probabilistic Graphical Models

Dec 05, 2012
Sameer Singh, Thore Graepel

* NIPS 2012 Workshop on Probabilistic Programming 

  Access Model/Code and Paper
SiGMa: Simple Greedy Matching for Aligning Large Knowledge Bases

Jul 19, 2012
Simon Lacoste-Julien, Konstantina Palla, Alex Davies, Gjergji Kasneci, Thore Graepel, Zoubin Ghahramani

* 10 pages + 2 pages appendix; 5 figures -- initial preprint 

  Access Model/Code and Paper
How To Grade a Test Without Knowing the Answers --- A Bayesian Graphical Model for Adaptive Crowdsourcing and Aptitude Testing

Jun 27, 2012
Yoram Bachrach, Thore Graepel, Tom Minka, John Guiver

* Appears in Proceedings of the 29th International Conference on Machine Learning (ICML 2012) 

  Access Model/Code and Paper
Kernel Topic Models

Oct 21, 2011
Philipp Hennig, David Stern, Ralf Herbrich, Thore Graepel

  Access Model/Code and Paper