Lars Buesing

Research

Department of Statistics, Columbia University

Show Academic Trajectory

Ego Network

D-Core

Research Interests

Author Statistics

Experience

Education

Bio

Currently, I am a research fellow at the Grossman Center for the Statistics of Mind and the Department of Statistics at Columbia University.

Papers55 papers

Sort

By YearBy Citation

On the role of planning in model-based deep reinforcement learning

Jessica B. Hamrick,Abram L. Friesen, Feryal Behbahani,Arthur Guez,Fabio Viola, Sims Witherspoon, Thomas Anthony,Lars Buesing, Petar Veličković,Théophane Weber

ICLR 2021, (2021)

Bibtex

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

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

Cited by1Bibtex

Counterfactual Credit Assignment in Model-Free Reinforcement Learning

Thomas Mesnard,Théophane Weber, Fabio Viola, Shantanu Thakoor, Alaa Saade,Anna Harutyunyan,Will Dabney, Tom Stepleton,Nicolas Heess,Arthur Guez, Marcus Hutter,Lars Buesing

Bibtex

Causally Correct Partial Models for Reinforcement Learning

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

Cited by2Bibtex

Representation Learning via Invariant Causal Mechanisms

Jovana Mitrovic, Brian McWilliams, Jacob Walker,Lars Buesing,Charles Blundell

international conference on learning representations, (2020)

Bibtex

Combining Q-Learning and Search with Amortized Value Estimates

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

ICLR, (2020)

Cited by7EIBibtex

Beyond Tabula-Rasa: a Modular Reinforcement Learning Approach for Physically Embedded 3D Sokoban

Peter Karkus,Mehdi Mirza,Arthur Guez, Andrew Jaegle,Timothy Lillicrap,Lars Buesing,Nicolas Heess,Theophane Weber

Bibtex

Physically Embedded Planning Problems: New Challenges for Reinforcement Learning

Mehdi Mirza, Andrew Jaegle,Jonathan J. Hunt,Arthur Guez, Saran Tunyasuvunakool, Alistair Muldal,Théophane Weber, Peter Karkus,Sébastien Racanière,Lars Buesing, Timothy Lillicrap,Nicolas Heess

Cited by1Bibtex

Value-driven Hindsight Modelling

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

NIPS 2020, (2020)

EIBibtex

Pointer Graph Networks

Veličković Petar,Buesing Lars, Overlan Matthew C.,Pascanu Razvan,Vinyals Oriol,Blundell Charles

NIPS 2020, (2020)

EIBibtex

Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search

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

ICLR, (2019)

EIBibtex

Credit Assignment Techniques in Stochastic Computation Graphs

Théophane Weber,Nicolas Heess,Lars Buesing,David Silver

international conference on artificial intelligence and statistics, (2019)

Cited by23EIBibtex

Temporal Difference Variational Auto-Encoder

Karol Gregor, George Papamakarios, Frederic Besse,Lars Buesing,Theophane Weber

ICLR, (2019)

Cited by48EIBibtex

Approximate Inference in Discrete Distributions with Monte Carlo Tree Search and Value Functions

Buesing Lars,Heess Nicolas,Weber Theophane

AISTATS, pp.624-634, (2019)

EIBibtex

Neural belief states for partially observed domains

Pol Moreno, Jan Humplik, George Papamakarios, Bernardo Avila Pires,Lars Buesing,Nicolas Heess,Théophane Weber

NeurIPS 2018 workshop on Reinforcement Learning under Partial Observability, (2018)

Cited by9Bibtex

Learning Dynamic State Abstractions for Model Based Reinforcement Learning

Lars Buesing,Theophane Weber, Sebastien Racaniere, SM Ali Eslami, Danilo Rezende, David Reichert,Fabio Viola, Frederic Besse, Karol Gregor, Demis Hassabis, Daan Wierstra

(2018)

Bibtex

Neural scene representation and rendering