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.
Here, we study the problem of how to train agents that collaborate well with human partners without using human data.
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.
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.
Neural networks have achieved success in a wide array of perceptual tasks but often fail at tasks involving both perception and higher-level reasoning.
Ranked #4 on Video Object Tracking on CATER
We show that EPNs learn to execute a value iteration-like planning algorithm and that they generalize to situations beyond their training experience.
The ability to decompose scenes in terms of abstract building blocks is crucial for general intelligence.
We show how to optimize these regularizers in a way that is easy to integrate with policy gradient reinforcement learning.
30 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.
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.
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.
We unpack these points in a series of seven proof-of-concept experiments, each of which examines a key aspect of deep meta-RL.
We learn recurrent neural network optimizers trained on simple synthetic functions by gradient descent.