Learning to Learn without Gradient Descent by Gradient Descent

no code implementations • ICML 2017 • Yutian Chen, Matthew W. Hoffman, Sergio Gomez Colmenarejo, Misha Denil, Timothy P. Lillicrap, Matt Botvinick, Nando de Freitas

We learn recurrent neural network optimizers trained on simple synthetic functions by gradient descent.

Bayesian Optimization

Learning to reinforcement learn

8 code implementations • 17 Nov 2016 • Jane. X. Wang, Zeb Kurth-Nelson, Dhruva Tirumala, Hubert Soyer, Joel Z. Leibo, Remi Munos, Charles Blundell, Dharshan Kumaran, Matt Botvinick

We unpack these points in a series of seven proof-of-concept experiments, each of which examines a key aspect of deep meta-RL.

Meta-Learning Meta Reinforcement Learning +2

Unsupervised Predictive Memory in a Goal-Directed Agent

1 code implementation • 28 Mar 2018 • Greg Wayne, Chia-Chun Hung, David Amos, Mehdi Mirza, Arun Ahuja, Agnieszka Grabska-Barwinska, Jack Rae, Piotr Mirowski, Joel Z. Leibo, Adam Santoro, Mevlana Gemici, Malcolm Reynolds, Tim Harley, Josh Abramson, Shakir Mohamed, Danilo Rezende, David Saxton, Adam Cain, Chloe Hillier, David Silver, Koray Kavukcuoglu, Matt Botvinick, Demis Hassabis, Timothy Lillicrap

Animals execute goal-directed behaviours despite the limited range and scope of their sensors.

Reinforcement Learning (RL)

Probing Physics Knowledge Using Tools from Developmental Psychology

no code implementations • 3 Apr 2018 • Luis Piloto, Ari Weinstein, Dhruva TB, Arun Ahuja, Mehdi Mirza, Greg Wayne, David Amos, Chia-Chun Hung, Matt Botvinick

While some work on this problem has taken the approach of building in components such as ready-made physics engines, other research aims to extract general physical concepts directly from sensory data.

Relational inductive biases, deep learning, and graph networks

31 code implementations • 4 Jun 2018 • Peter W. Battaglia, Jessica B. Hamrick, Victor Bapst, Alvaro Sanchez-Gonzalez, Vinicius Zambaldi, Mateusz Malinowski, Andrea Tacchetti, David Raposo, Adam Santoro, Ryan Faulkner, Caglar Gulcehre, Francis Song, Andrew Ballard, Justin Gilmer, George Dahl, Ashish Vaswani, Kelsey Allen, Charles Nash, Victoria Langston, Chris Dyer, Nicolas Heess, Daan Wierstra, Pushmeet Kohli, Matt Botvinick, Oriol Vinyals, Yujia Li, Razvan Pascanu

As a companion to this paper, we have released an open-source software library for building graph networks, with demonstrations of how to use them in practice.

Decision Making Inductive Bias +1

Learning to Share and Hide Intentions using Information Regularization

1 code implementation • NeurIPS 2018 • DJ Strouse, Max Kleiman-Weiner, Josh Tenenbaum, Matt Botvinick, David Schwab

We show how to optimize these regularizers in a way that is easy to integrate with policy gradient reinforcement learning.

Multi-agent Reinforcement Learning reinforcement-learning +1

MONet: Unsupervised Scene Decomposition and Representation

5 code implementations • 22 Jan 2019 • Christopher P. Burgess, Loic Matthey, Nicholas Watters, Rishabh Kabra, Irina Higgins, Matt Botvinick, Alexander Lerchner

The ability to decompose scenes in terms of abstract building blocks is crucial for general intelligence.

Object Discovery Unsupervised Object Segmentation

Rapid Task-Solving in Novel Environments

no code implementations • ICLR 2021 • Sam Ritter, Ryan Faulkner, Laurent Sartran, Adam Santoro, Matt Botvinick, David Raposo

We show that EPNs learn to execute a value iteration-like planning algorithm and that they generalize to situations beyond their training experience.

Navigate

Attention over learned object embeddings enables complex visual reasoning

1 code implementation • NeurIPS 2021 • David Ding, Felix Hill, Adam Santoro, Malcolm Reynolds, Matt Botvinick

Neural networks have achieved success in a wide array of perceptual tasks but often fail at tasks involving both perception and higher-level reasoning.

Object Video Object Tracking +1

Synthetic Returns for Long-Term Credit Assignment

2 code implementations • 24 Feb 2021 • David Raposo, Sam Ritter, Adam Santoro, Greg Wayne, Theophane Weber, Matt Botvinick, Hado van Hasselt, Francis Song

We propose state-associative (SA) learning, where the agent learns associations between states and arbitrarily distant future rewards, then propagates credit directly between the two.

A multi-agent reinforcement learning model of reputation and cooperation in human groups

no code implementations • 8 Mar 2021 • Kevin R. McKee, Edward Hughes, Tina O. Zhu, Martin J. Chadwick, Raphael Koster, Antonio Garcia Castaneda, Charlie Beattie, Thore Graepel, Matt Botvinick, Joel Z. Leibo

Collective action demands that individuals efficiently coordinate how much, where, and when to cooperate.

Multi-agent Reinforcement Learning reinforcement-learning +1

Collaborating with Humans without Human Data

1 code implementation • NeurIPS 2021 • DJ Strouse, Kevin R. McKee, Matt Botvinick, Edward Hughes, Richard Everett

Here, we study the problem of how to train agents that collaborate well with human partners without using human data.

Multi-agent Reinforcement Learning

HiP: Hierarchical Perceiver

2 code implementations • 22 Feb 2022 • Joao Carreira, Skanda Koppula, Daniel Zoran, Adria Recasens, Catalin Ionescu, Olivier Henaff, Evan Shelhamer, Relja Arandjelovic, Matt Botvinick, Oriol Vinyals, Karen Simonyan, Andrew Zisserman, Andrew Jaegle

This however hinders them from scaling up to the inputs sizes required to process raw high-resolution images or video.