10.1k citations · 22.1k across the 78 of their papers we have counts for
52 papers · 1 filter
Can foundation models actively gather information in interactive environments to test hypotheses?
Danny P. Sawyer, Nan Rosemary Ke, Hubert Soyer +9
Foundation models excel at single-turn reasoning but struggle with multi-turn exploration in dynamic environments, a requirement for many real-world challenges. We evaluated these…
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
David Raposo, Sam Ritter, Blake Richards +3
Transformer-based language models spread FLOPs uniformly across input sequences. In this work we demonstrate that transformers can instead learn to dynamically allocate FLOPs (or c…
Android in the Wild: A Large-Scale Dataset for Android Device Control
Christopher Rawles, Alice Li, Daniel Rodriguez +2
There is a growing interest in device-control systems that can interpret human natural language instructions and execute them on a digital device by directly controlling its user i…
Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback
Josh Abramson, Arun Ahuja, Federico Carnevale +16
An important goal in artificial intelligence is to create agents that can both interact naturally with humans and learn from their feedback. Here we demonstrate how to use reinforc…
Intra-agent speech permits zero-shot task acquisition
Chen Yan, Federico Carnevale, Petko Georgiev +7
Human language learners are exposed to a trickle of informative, context-sensitive language, but a flood of raw sensory data. Through both social language use and internal processe…
Large-Scale Retrieval for Reinforcement Learning
Peter C. Humphreys, Arthur Guez, Olivier Tieleman +3
Effective decision making involves flexibly relating past experiences and relevant contextual information to a novel situation. In deep reinforcement learning (RL), the dominant pa…
Evaluating Multimodal Interactive Agents
Josh Abramson, Arun Ahuja, Federico Carnevale +12
Creating agents that can interact naturally with humans is a common goal in artificial intelligence (AI) research. However, evaluating these interactions is challenging: collecting…
Equilibrium Aggregation: Encoding Sets via Optimization
Sergey Bartunov, Fabian B. Fuchs, Timothy Lillicrap
Processing sets or other unordered, potentially variable-sized inputs in neural networks is usually handled by aggregating a number of input tensors into a single representation. W…
Retrieval-Augmented Reinforcement Learning
Anirudh Goyal, Abram L. Friesen, Andrea Banino +13
Most deep reinforcement learning (RL) algorithms distill experience into parametric behavior policies or value functions via gradient updates. While effective, this approach has se…
A data-driven approach for learning to control computers
Peter C Humphreys, David Raposo, Toby Pohlen +8
It would be useful for machines to use computers as humans do so that they can aid us in everyday tasks. This is a setting in which there is also the potential to leverage large-sc…
Towards Biologically Plausible Convolutional Networks
Roman Pogodin, Yash Mehta, Timothy P. Lillicrap +1
Convolutional networks are ubiquitous in deep learning. They are particularly useful for images, as they reduce the number of parameters, reduce training time, and increase accurac…
Imitating Interactive Intelligence
Josh Abramson, Arun Ahuja, Iain Barr +26
A common vision from science fiction is that robots will one day inhabit our physical spaces, sense the world as we do, assist our physical labours, and communicate with us through…
Beyond Tabula-Rasa: a Modular Reinforcement Learning Approach for Physically Embedded 3D Sokoban
Peter Karkus, Mehdi Mirza, Arthur Guez +5
Intelligent robots need to achieve abstract objectives using concrete, spatiotemporally complex sensory information and motor control. Tabula rasa deep reinforcement learning (RL)…
Mastering Atari with Discrete World Models
Danijar Hafner, Timothy Lillicrap, Mohammad Norouzi +1
Intelligent agents need to generalize from past experience to achieve goals in complex environments. World models facilitate such generalization and allow learning behaviors from i…
Dream to Control: Learning Behaviors by Latent Imagination
Danijar Hafner, Timothy Lillicrap, Jimmy Ba +1
Learned world models summarize an agent's experience to facilitate learning complex behaviors. While learning world models from high-dimensional sensory inputs is becoming feasible…
LOGAN: Latent Optimisation for Generative Adversarial Networks
Yan Wu, Jeff Donahue, David Balduzzi +2
Training generative adversarial networks requires balancing of delicate adversarial dynamics. Even with careful tuning, training may diverge or end up in a bad equilibrium with dro…
Compressive Transformers for Long-Range Sequence Modelling
Jack W. Rae, Anna Potapenko, Siddhant M. Jayakumar +1
We present the Compressive Transformer, an attentive sequence model which compresses past memories for long-range sequence learning. We find the Compressive Transformer obtains sta…
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Julian Schrittwieser, Ioannis Antonoglou, Thomas Hubert +9
Constructing agents with planning capabilities has long been one of the main challenges in the pursuit of artificial intelligence. Tree-based planning methods have enjoyed huge suc…
Automated curricula through setter-solver interactions
Sebastien Racaniere, Andrew K. Lampinen, Adam Santoro +3
Reinforcement learning algorithms use correlations between policies and rewards to improve agent performance. But in dynamic or sparsely rewarding environments these correlations a…
What does it mean to understand a neural network?
Timothy P. Lillicrap, Konrad P. Kording
We can define a neural network that can learn to recognize objects in less than 100 lines of code. However, after training, it is characterized by millions of weights that contain…
Meta-Learning Neural Bloom Filters
Jack W Rae, Sergey Bartunov, Timothy P Lillicrap
There has been a recent trend in training neural networks to replace data structures that have been crafted by hand, with an aim for faster execution, better accuracy, or greater c…
Deep Compressed Sensing
Yan Wu, Mihaela Rosca, Timothy Lillicrap
Compressed sensing (CS) provides an elegant framework for recovering sparse signals from compressed measurements. For example, CS can exploit the structure of natural images and re…
Deep Learning without Weight Transport
Mohamed Akrout, Collin Wilson, Peter C. Humphreys +2
Current algorithms for deep learning probably cannot run in the brain because they rely on weight transport, where forward-path neurons transmit their synaptic weights to a feedbac…
An investigation of model-free planning
Arthur Guez, Mehdi Mirza, Karol Gregor +10
The field of reinforcement learning (RL) is facing increasingly challenging domains with combinatorial complexity. For an RL agent to address these challenges, it is essential that…