Vinicius Zambaldi — accepted AI-conference papers

2020

MEMO: A Deep Network for Flexible Combination of Episodic Memories

Andrea Banino, Adrià Puigdomènech Badia, Raphael Köster, Martin J. Chadwick, Vinicius Zambaldi, Demis Hassabis +4

ICLR 2020poster

Recent research developing neural network architectures with external memory have often used the benchmark bAbI question and answering dataset which provides a challenging number of tasks requiring reasoning. Here we employed a classic associative inference task from the human neuroscience literatur…

Cited by 0 Source ↗Scholar ↗

2019

CompILE: Compositional Imitation Learning and Execution

Thomas Kipf, Yujia Li, Hanjun Dai, Vinicius Zambaldi, Alvaro Sanchez-Gonzalez, Edward Grefenstette +2

ICML 2019oral

We introduce Compositional Imitation Learning and Execution (CompILE): a framework for learning reusable, variable-length segments of hierarchically-structured behavior from demonstration data. CompILE uses a novel unsupervised, fully-differentiable sequence segmentation module to learn latent encod…

Cited by 163 Source ↗PDF ↗code ↗Scholar ↗

2019

Deep reinforcement learning with relational inductive biases

Vinicius Zambaldi, David Raposo, Adam Santoro, Victor Bapst, Yujia Li, Igor Babuschkin +10

ICLR 2019poster

We introduce an approach for augmenting model-free deep reinforcement learning agents with a mechanism for relational reasoning over structured representations, which improves performance, learning efficiency, generalization, and interpretability. Our architecture encodes an image as a set of vector…

Cited by 265 Source ↗PDF ↗Scholar ↗

2019

Relational Forward Models for Multi-Agent Learning

Andrea Tacchetti, H. Francis Song, Pedro A. M. Mediano, Vinicius Zambaldi, János Kramár, Neil C. Rabinowitz +3

ICLR 2019poster

The behavioral dynamics of multi-agent systems have a rich and orderly structure, which can be leveraged to understand these systems, and to improve how artificial agents learn to operate in them. Here we introduce Relational Forward Models (RFM) for multi-agent learning, networks that can learn to…

Cited by 95 Source ↗PDF ↗Scholar ↗

2018

Actor-Critic Policy Optimization in Partially Observable Multiagent Environments

Sriram Srinivasan, Marc Lanctot, Vinicius Zambaldi, Julien Perolat, Karl Tuyls, Remi Munos +1

NeurIPS 2018poster

Optimization of parameterized policies for reinforcement learning (RL) is an important and challenging problem in artificial intelligence. Among the most common approaches are algorithms based on gradient ascent of a score function representing discounted return. In this paper, we examine the role o…

Cited by 178 Source ↗PDF ↗code ↗Scholar ↗

2017

A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning

Marc Lanctot, Vinicius Zambaldi, Audrunas Gruslys, Angeliki Lazaridou, Karl Tuyls, Julien Perolat +2

NeurIPS 2017poster

There has been a resurgence of interest in multiagent reinforcement learning (MARL), due partly to the recent success of deep neural networks. The simplest form of MARL is independent reinforcement learning (InRL), where each agent treats all of its experience as part of its (non stationary) environ…

Cited by 870 Source ↗PDF ↗code ↗Scholar ↗

2017

A multi-agent reinforcement learning model of common-pool resource appropriation

Julien Pérolat, Joel Z. Leibo, Vinicius Zambaldi, Charles Beattie, Karl Tuyls, Thore Graepel

NeurIPS 2017poster

Humanity faces numerous problems of common-pool resource appropriation. This class of multi-agent social dilemma includes the problems of ensuring sustainable use of fresh water, common fisheries, grazing pastures, and irrigation systems. Abstract models of common-pool resource appropriation based o…

Cited by 254 Source ↗PDF ↗Scholar ↗