Alvaro Sanchez-Gonzalez

is this you? claim profile

0 followers
Google

Learning Mesh-Based Simulation with Graph Networks

Mesh-based simulations are central to modeling complex physical systems ...
10/07/2020 ∙ by Tobias Pfaff, et al. ∙ 0 ∙ share

read it
Discovering Symbolic Models from Deep Learning with Inductive Biases

We develop a general approach to distill symbolic representations of a l...
06/19/2020 ∙ by Miles Cranmer, et al. ∙ 12 ∙ share

read it
Learning to Simulate Complex Physics with Graph Networks

Here we present a general framework for learning simulation, and provide...
02/21/2020 ∙ by Alvaro Sanchez-Gonzalez, et al. ∙ 26 ∙ share

read it
Combining Q-Learning and Search with Amortized Value Estimates

We introduce "Search with Amortized Value Estimates" (SAVE), an approach...
12/05/2019 ∙ by Jessica B. Hamrick, et al. ∙ 0 ∙ share

read it
Object-oriented state editing for HRL

We introduce agents that use object-oriented reasoning to consider alter...
10/31/2019 ∙ by Victor Bapst, et al. ∙ 0 ∙ share

read it
Hamiltonian Graph Networks with ODE Integrators

We introduce an approach for imposing physically informed inductive bias...
09/27/2019 ∙ by Alvaro Sanchez-Gonzalez, et al. ∙ 0 ∙ share

read it
Structured agents for physical construction

Physical construction -- the ability to compose objects, subject to phys...
04/05/2019 ∙ by Victor Bapst, et al. ∙ 20 ∙ share

read it
Relational inductive biases, deep learning, and graph networks

Artificial intelligence (AI) has undergone a renaissance recently, makin...
06/04/2018 ∙ by Peter W. Battaglia, et al. ∙ 0 ∙ share

read it
Graph networks as learnable physics engines for inference and control

Understanding and interacting with everyday physical scenes requires ric...
06/04/2018 ∙ by Alvaro Sanchez-Gonzalez, et al. ∙ 2 ∙ share

read it

Alvaro Sanchez-Gonzalez

Featured Co-authors

Jure Leskovec

Pushmeet Kohli

Oriol Vinyals

Chris Dyer

Nicolas Heess

Razvan Pascanu

Satinder Singh

Caglar Gulcehre

Martin Riedmiller

Kyle Cranmer

Jost Tobias Springenberg

Learning Mesh-Based Simulation with Graph Networks

Discovering Symbolic Models from Deep Learning with Inductive Biases

Learning to Simulate Complex Physics with Graph Networks

Combining Q-Learning and Search with Amortized Value Estimates

Object-oriented state editing for HRL

Hamiltonian Graph Networks with ODE Integrators

Structured agents for physical construction

Relational inductive biases, deep learning, and graph networks

Graph networks as learnable physics engines for inference and control