
Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems
Modeling a structured, dynamic environment like a video game requires ke...
read it

Pointer Graph Networks
Graph neural networks (GNNs) are typically applied to static graphs that...
read it

Agent57: Outperforming the Atari Human Benchmark
Atari games have been a longstanding benchmark in the reinforcement lea...
read it

Never Give Up: Learning Directed Exploration Strategies
We propose a reinforcement learning agent to solve hard exploration game...
read it

Targeted free energy estimation via learned mappings
Free energy perturbation (FEP) was proposed by Zwanzig more than six dec...
read it

MEMO: A Deep Network for Flexible Combination of Episodic Memories
Recent research developing neural network architectures with external me...
read it

Shaping representations through communication: community size effect in artificial learning systems
Motivated by theories of language and communication that explain why com...
read it

Generalization of Reinforcement Learners with Working and Episodic Memory
Memory is an important aspect of intelligence and plays a role in many d...
read it

Neural Execution of Graph Algorithms
Graph Neural Networks (GNNs) are a powerful representational tool for so...
read it

Fast deep reinforcement learning using online adjustments from the past
We propose Ephemeral Value Adjusments (EVA): a means of allowing deep re...
read it

Been There, Done That: MetaLearning with Episodic Recall
Metalearning agents excel at rapidly learning new tasks from openended...
read it

Pushing the bounds of dropout
We show that dropout training is best understood as performing MAP estim...
read it

Memorybased Parameter Adaptation
Deep neural networks have excelled on a wide range of problems, from vis...
read it

DARLA: Improving ZeroShot Transfer in Reinforcement Learning
Domain adaptation is an important open problem in deep reinforcement lea...
read it

Noisy Networks for Exploration
We introduce NoisyNet, a deep reinforcement learning agent with parametr...
read it

Bayesian Recurrent Neural Networks
In this work we explore a straightforward variational Bayes scheme for R...
read it

Neural Episodic Control
Deep reinforcement learning methods attain superhuman performance in a ...
read it

PathNet: Evolution Channels Gradient Descent in Super Neural Networks
For artificial general intelligence (AGI) it would be efficient if multi...
read it

Learning to reinforcement learn
In recent years deep reinforcement learning (RL) systems have attained s...
read it

Early Visual Concept Learning with Unsupervised Deep Learning
Automated discovery of early visual concepts from raw image data is a ma...
read it

ModelFree Episodic Control
State of the art deep reinforcement learning algorithms take many millio...
read it

Matching Networks for One Shot Learning
Learning from a few examples remains a key challenge in machine learning...
read it

Deep Exploration via Bootstrapped DQN
Efficient exploration in complex environments remains a major challenge ...
read it

Distributed Bayesian Learning with Stochastic Naturalgradient Expectation Propagation and the Posterior Server
This paper makes two contributions to Bayesian machine learning algorith...
read it

Weight Uncertainty in Neural Networks
We introduce a new, efficient, principled and backpropagationcompatible...
read it

The Bayesian Echo Chamber: Modeling Social Influence via Linguistic Accommodation
We present the Bayesian Echo Chamber, a new Bayesian generative model fo...
read it

Bayesian Rose Trees
Hierarchical structure is ubiquitous in data across many domains. There ...
read it

Mixed Cumulative Distribution Networks
Directed acyclic graphs (DAGs) are a popular framework to express multiv...
read it