7.8k citations · 10.3k across the 19 of their papers we have counts for
21 papers
TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models
Jinho Choo, JunSeung Lee, Jimyeong Kim +3
Large language models (LLMs) demonstrate strong multilingual capabilities, yet often fail to consistently generate responses in the intended language, exhibiting a phenomenon known…
Explainability Via Causal Self-Talk
Nicholas A. Roy, Junkyung Kim, Neil Rabinowitz
Explaining the behavior of AI systems is an important problem that, in practice, is generally avoided. While the XAI community has been developing an abundance of techniques, most…
Semantic Exploration from Language Abstractions and Pretrained Representations
Allison C. Tam, Neil C. Rabinowitz, Andrew K. Lampinen +6
Effective exploration is a challenge in reinforcement learning (RL). Novelty-based exploration methods can suffer in high-dimensional state spaces, such as continuous partially-obs…
Tell me why! Explanations support learning relational and causal structure
Andrew K. Lampinen, Nicholas A. Roy, Ishita Dasgupta +8
Inferring the abstract relational and causal structure of the world is a major challenge for reinforcement-learning (RL) agents. For humans, language--particularly in the form of e…
Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents
Jane X. Wang, Michael King, Nicolas Porcel +14
There has been rapidly growing interest in meta-learning as a method for increasing the flexibility and sample efficiency of reinforcement learning. One problem in this area of res…
Should I tear down this wall? Optimizing social metrics by evaluating novel actions
János Kramár, Neil Rabinowitz, Tom Eccles +1
One of the fundamental challenges of governance is deciding when and how to intervene in multi-agent systems in order to impact group-wide metrics of success. This is particularly…
Making Efficient Use of Demonstrations to Solve Hard Exploration Problems
Tom Le Paine, Caglar Gulcehre, Bobak Shahriari +11
This paper introduces R2D3, an agent that makes efficient use of demonstrations to solve hard exploration problems in partially observable environments with highly variable initial…
Meta-learners' learning dynamics are unlike learners'
Neil C. Rabinowitz
Meta-learning is a tool that allows us to build sample-efficient learning systems. Here we show that, once meta-trained, LSTM Meta-Learners aren't just faster learners than their s…
Meta-learning of Sequential Strategies
Pedro A. Ortega, Jane X. Wang, Mark Rowland +21
In this report we review memory-based meta-learning as a tool for building sample-efficient strategies that learn from past experience to adapt to any task within a target class. O…
Relational Forward Models for Multi-Agent Learning
Andrea Tacchetti, H. Francis Song, Pedro A. M. Mediano +5
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…
Human-level performance in first-person multiplayer games with population-based deep reinforcement learning
Max Jaderberg, Wojciech M. Czarnecki, Iain Dunning +15
Recent progress in artificial intelligence through reinforcement learning (RL) has shown great success on increasingly complex single-agent environments and two-player turn-based g…
Pooling is neither necessary nor sufficient for appropriate deformation stability in CNNs
Avraham Ruderman, Neil C. Rabinowitz, Ari S. Morcos +1
Many of our core assumptions about how neural networks operate remain empirically untested. One common assumption is that convolutional neural networks need to be stable to small t…
Machine Theory of Mind
Neil C. Rabinowitz, Frank Perbet, H. Francis Song +3
Theory of mind (ToM; Premack & Woodruff, 1978) broadly refers to humans' ability to represent the mental states of others, including their desires, beliefs, and intentions. We prop…
On the importance of single directions for generalization
Ari S. Morcos, David G. T. Barrett, Neil C. Rabinowitz +1
Despite their ability to memorize large datasets, deep neural networks often achieve good generalization performance. However, the differences between the learned solutions of netw…
Building Machines that Learn and Think for Themselves: Commentary on Lake et al., Behavioral and Brain Sciences, 2017
M. Botvinick, D. G. T. Barrett, P. Battaglia +16
We agree with Lake and colleagues on their list of key ingredients for building humanlike intelligence, including the idea that model-based reasoning is essential. However, we favo…
Overcoming catastrophic forgetting in neural networks
James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz +11
The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence. Neural networks are not, in general, capable of this and it has been wi…
The Predictron: End-To-End Learning and Planning
David Silver, Hado van Hasselt, Matteo Hessel +8
One of the key challenges of artificial intelligence is to learn models that are effective in the context of planning. In this document we introduce the predictron architecture. Th…
Progressive Neural Networks
Andrei A. Rusu, Neil C. Rabinowitz, Guillaume Desjardins +5
Learning to solve complex sequences of tasks--while both leveraging transfer and avoiding catastrophic forgetting--remains a key obstacle to achieving human-level intelligence. The…
Building Machines That Learn and Think Like People
Brenden M. Lake, Tomer D. Ullman, Joshua B. Tenenbaum +1
Recent progress in artificial intelligence (AI) has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks t…
A model of sensory neural responses in the presence of unknown modulatory inputs
Neil C. Rabinowitz, Robbe L. T. Goris, Johannes Ballé +1
Neural responses are highly variable, and some portion of this variability arises from fluctuations in modulatory factors that alter their gain, such as adaptation, attention, arou…
The local low-dimensionality of natural images
Olivier J. Hénaff, Johannes Ballé, Neil C. Rabinowitz +1
We develop a new statistical model for photographic images, in which the local responses of a bank of linear filters are described as jointly Gaussian, with zero mean and a covaria…