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 Tim Genewein

Causal Analysis of Agent Behavior for AI Safety


Mar 05, 2021
Grégoire Déletang, Jordi Grau-Moya, Miljan Martic, Tim Genewein, Tom McGrath, Vladimir Mikulik, Markus Kunesch, Shane Legg, Pedro A. Ortega

* 16 pages, 16 figures, 6 tables 

  Access Paper or Ask Questions

Algorithms for Causal Reasoning in Probability Trees


Nov 12, 2020
Tim Genewein, Tom McGrath, Grégoire Déletang, Vladimir Mikulik, Miljan Martic, Shane Legg, Pedro A. Ortega

* (2nd version with correction to algorithm) 11 pages, 8 figures, 5 algorithms. A companion Colaboratory tutorial is available at https://github.com/deepmind/deepmind-research/tree/master/causal_reasoning 

  Access Paper or Ask Questions

Meta-trained agents implement Bayes-optimal agents


Oct 21, 2020
Vladimir Mikulik, Grégoire Delétang, Tom McGrath, Tim Genewein, Miljan Martic, Shane Legg, Pedro A. Ortega

* Published at 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada 

  Access Paper or Ask Questions

Group Pruning using a Bounded-Lp norm for Group Gating and Regularization


Aug 09, 2019
Chaithanya Kumar Mummadi, Tim Genewein, Dan Zhang, Thomas Brox, Volker Fischer

* German Conference on Pattern Recognition (GCPR) 2019, 12 main pages, 3 pages of appendix, 4 figures, 2 tables 

  Access Paper or Ask Questions

Meta-learning of Sequential Strategies


May 08, 2019
Pedro A. Ortega, Jane X. Wang, Mark Rowland, Tim Genewein, Zeb Kurth-Nelson, Razvan Pascanu, Nicolas Heess, Joel Veness, Alex Pritzel, Pablo Sprechmann, Siddhant M. Jayakumar, Tom McGrath, Kevin Miller, Mohammad Azar, Ian Osband, Neil Rabinowitz, András György, Silvia Chiappa, Simon Osindero, Yee Whye Teh, Hado van Hasselt, Nando de Freitas, Matthew Botvinick, Shane Legg

* DeepMind Technical Report (15 pages, 6 figures) 

  Access Paper or Ask Questions

Sinkhorn AutoEncoders


Oct 03, 2018
Giorgio Patrini, Marcello Carioni, Patrick Forré, Samarth Bhargav, Max Welling, Rianne van den Berg, Tim Genewein, Frank Nielsen

* Submitted to ICLR19 

  Access Paper or Ask Questions

An information-theoretic on-line update principle for perception-action coupling


Apr 16, 2018
Zhen Peng, Tim Genewein, Felix Leibfried, Daniel A. Braun

* 8 pages, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 

  Access Paper or Ask Questions

On Detecting Adversarial Perturbations


Feb 21, 2017
Jan Hendrik Metzen, Tim Genewein, Volker Fischer, Bastian Bischoff

* Final version for ICLR2017 (see https://openreview.net/forum?id=SJzCSf9xg&noteId=SJzCSf9xg

  Access Paper or Ask Questions

Planning with Information-Processing Constraints and Model Uncertainty in Markov Decision Processes


Apr 07, 2016
Jordi Grau-Moya, Felix Leibfried, Tim Genewein, Daniel A. Braun

* 16 pages, 3 figures 

  Access Paper or Ask Questions

Abstraction in decision-makers with limited information processing capabilities


Dec 19, 2013
Tim Genewein, Daniel A. Braun

* Presented at the NIPS 2013 Workshop on Planning with Information Constraints 

  Access Paper or Ask Questions

A Nonparametric Conjugate Prior Distribution for the Maximizing Argument of a Noisy Function


Nov 10, 2012
Pedro A. Ortega, Jordi Grau-Moya, Tim Genewein, David Balduzzi, Daniel A. Braun

* Neural Information Processing Systems (NIPS) 2012 
* 9 pages, 5 figures 

  Access Paper or Ask Questions