Search Results for author:
Found 11 papers, 3 papers with code
Semantic Exploration from Language Abstractions and Pretrained Representations
We show that these pretrained representations drive meaningful, task-relevant exploration and improve performance on 3D simulated environments.
Tell me why! Explanations support learning relational and causal structure
Inferring the abstract relational and causal structure of the world is a major challenge for reinforcement-learning (RL) agents.
Meta-learners' learning dynamics are unlike learners'
Meta-learning is a tool that allows us to build sample-efficient learning systems.
Relational Forward Models for Multi-Agent Learning
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.
Human-level performance in first-person multiplayer games with population-based deep reinforcement learning
Recent progress in artificial intelligence through reinforcement learning (RL) has shown great success on increasingly complex single-agent environments and two-player turn-based games.
Pooling is neither necessary nor sufficient for appropriate deformation stability in CNNs
In this work, we rigorously test these questions, and find that deformation stability in convolutional networks is more nuanced than it first appears: (1) Deformation invariance is not a binary property, but rather that different tasks require different degrees of deformation stability at different layers.
On the importance of single directions for generalization
Finally, we find that class selectivity is a poor predictor of task importance, suggesting not only that networks which generalize well minimize their dependence on individual units by reducing their selectivity, but also that individually selective units may not be necessary for strong network performance.
Machine Theory of Mind
We design a Theory of Mind neural network -- a ToMnet -- which uses meta-learning to build models of the agents it encounters, from observations of their behaviour alone.
Progressive Neural Networks
Learning to solve complex sequences of tasks--while both leveraging transfer and avoiding catastrophic forgetting--remains a key obstacle to achieving human-level intelligence.
A model of sensory neural responses in the presence of unknown modulatory inputs
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, arousal, expected or actual reward, emotion, and local metabolic resource availability.
The local low-dimensionality of natural images
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 covariance that varies slowly over spatial position.
