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 Valentin Dalibard

Open-Ended Learning Leads to Generally Capable Agents

Jul 31, 2021
Open Ended Learning Team, Adam Stooke, Anuj Mahajan, Catarina Barros, Charlie Deck, Jakob Bauer, Jakub Sygnowski, Maja Trebacz, Max Jaderberg, Michael Mathieu, Nat McAleese, Nathalie Bradley-Schmieg, Nathaniel Wong, Nicolas Porcel, Roberta Raileanu, Steph Hughes-Fitt, Valentin Dalibard, Wojciech Marian Czarnecki

  Access Paper or Ask Questions

Perception-Prediction-Reaction Agents for Deep Reinforcement Learning

Jun 26, 2020
Adam Stooke, Valentin Dalibard, Siddhant M. Jayakumar, Wojciech M. Czarnecki, Max Jaderberg

  Access Paper or Ask Questions

A Generalized Framework for Population Based Training

Feb 05, 2019
Ang Li, Ola Spyra, Sagi Perel, Valentin Dalibard, Max Jaderberg, Chenjie Gu, David Budden, Tim Harley, Pramod Gupta

* 9 pages 

  Access Paper or Ask Questions

Population Based Training of Neural Networks

Nov 28, 2017
Max Jaderberg, Valentin Dalibard, Simon Osindero, Wojciech M. Czarnecki, Jeff Donahue, Ali Razavi, Oriol Vinyals, Tim Green, Iain Dunning, Karen Simonyan, Chrisantha Fernando, Koray Kavukcuoglu

  Access Paper or Ask Questions

Tuning the Scheduling of Distributed Stochastic Gradient Descent with Bayesian Optimization

Dec 01, 2016
Valentin Dalibard, Michael Schaarschmidt, Eiko Yoneki

  Access Paper or Ask Questions

Learning Runtime Parameters in Computer Systems with Delayed Experience Injection

Oct 31, 2016
Michael Schaarschmidt, Felix Gessert, Valentin Dalibard, Eiko Yoneki

* Deep Reinforcement Learning Workshop, NIPS 2016 

  Access Paper or Ask Questions