Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planning

Apr 23, 2020
Giambattista Parascandolo, Lars Buesing, Josh Merel, Leonard Hasenclever, John Aslanides, Jessica B. Hamrick, Nicolas Heess, Alexander Neitz, Theophane Weber


  Access Model/Code and Paper
Value-driven Hindsight Modelling

Feb 19, 2020
Arthur Guez, Fabio Viola, Théophane Weber, Lars Buesing, Steven Kapturowski, Doina Precup, David Silver, Nicolas Heess

* 8 pages + reference + appendix 

  Access Model/Code and Paper
Causally Correct Partial Models for Reinforcement Learning

Feb 07, 2020
Danilo J. Rezende, Ivo Danihelka, George Papamakarios, Nan Rosemary Ke, Ray Jiang, Theophane Weber, Karol Gregor, Hamza Merzic, Fabio Viola, Jane Wang, Jovana Mitrovic, Frederic Besse, Ioannis Antonoglou, Lars Buesing


  Access Model/Code and Paper
Combining Q-Learning and Search with Amortized Value Estimates

Jan 10, 2020
Jessica B. Hamrick, Victor Bapst, Alvaro Sanchez-Gonzalez, Tobias Pfaff, Theophane Weber, Lars Buesing, Peter W. Battaglia

* Published as a conference paper at ICLR 2020 

  Access Model/Code and Paper
Approximate Inference in Discrete Distributions with Monte Carlo Tree Search and Value Functions

Oct 15, 2019
Lars Buesing, Nicolas Heess, Theophane Weber


  Access Model/Code and Paper
Credit Assignment Techniques in Stochastic Computation Graphs

Jan 07, 2019
Théophane Weber, Nicolas Heess, Lars Buesing, David Silver


  Access Model/Code and Paper
Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search

Nov 15, 2018
Lars Buesing, Theophane Weber, Yori Zwols, Sebastien Racaniere, Arthur Guez, Jean-Baptiste Lespiau, Nicolas Heess


  Access Model/Code and Paper
Imagination-Augmented Agents for Deep Reinforcement Learning

Feb 14, 2018
Théophane Weber, Sébastien Racanière, David P. Reichert, Lars Buesing, Arthur Guez, Danilo Jimenez Rezende, Adria Puigdomènech Badia, Oriol Vinyals, Nicolas Heess, Yujia Li, Razvan Pascanu, Peter Battaglia, Demis Hassabis, David Silver, Daan Wierstra


  Access Model/Code and Paper
Learning and Querying Fast Generative Models for Reinforcement Learning

Feb 08, 2018
Lars Buesing, Theophane Weber, Sebastien Racaniere, S. M. Ali Eslami, Danilo Rezende, David P. Reichert, Fabio Viola, Frederic Besse, Karol Gregor, Demis Hassabis, Daan Wierstra


  Access Model/Code and Paper
Fast amortized inference of neural activity from calcium imaging data with variational autoencoders

Nov 06, 2017
Artur Speiser, Jinyao Yan, Evan Archer, Lars Buesing, Srinivas C. Turaga, Jakob H. Macke

* NIPS 2017 

  Access Model/Code and Paper
Learning model-based planning from scratch

Jul 19, 2017
Razvan Pascanu, Yujia Li, Oriol Vinyals, Nicolas Heess, Lars Buesing, Sebastien Racanière, David Reichert, Théophane Weber, Daan Wierstra, Peter Battaglia


  Access Model/Code and Paper
Bayesian Manifold Learning: The Locally Linear Latent Variable Model (LL-LVM)

Dec 01, 2015
Mijung Park, Wittawat Jitkrittum, Ahmad Qamar, Zoltan Szabo, Lars Buesing, Maneesh Sahani

* accepted to NIPS 2015 

  Access Model/Code and Paper
Black box variational inference for state space models

Nov 23, 2015
Evan Archer, Il Memming Park, Lars Buesing, John Cunningham, Liam Paninski


  Access Model/Code and Paper