• Publications
  • Influence
Exploration by Random Network Distillation
We introduce an exploration bonus for deep reinforcement learning methods that is easy to implement and adds minimal overhead to the computation performed. The bonus is the error of a neural networkExpand
  • 221
  • 67
Large-Scale Study of Curiosity-Driven Learning
Reinforcement learning algorithms rely on carefully engineering environment rewards that are extrinsic to the agent. However, annotating each environment with hand-designed, dense rewards is notExpand
  • 212
  • 41
Data Augmentation Generative Adversarial Networks
Effective training of neural networks requires much data. In the low-data regime, parameters are underdetermined, and learnt networks generalise poorly. Data AugmentationExpand
  • 303
  • 31
Censoring Representations with an Adversary
In practice, there are often explicit constraints on what representations or decisions are acceptable in an application of machine learning. For example it may be a legal requirement that a decisionExpand
  • 207
  • 28
Three Factors Influencing Minima in SGD
We study the statistical properties of the endpoint of stochastic gradient descent (SGD). We approximate SGD as a stochastic differential equation (SDE) and consider its Boltzmann Gibbs equilibriumExpand
  • 148
  • 25
Towards a Neural Statistician
An efficient learner is one who reuses what they already know to tackle a new problem. For a machine learner, this means understanding the similarities amongst datasets. In order to do this, one mustExpand
  • 196
  • 24
How to train your MAML
The field of few-shot learning has recently seen substantial advancements. Most of these advancements came from casting few-shot learning as a meta-learning problem. Model Agnostic Meta Learning orExpand
  • 113
  • 23
Probabilistic inference for solving discrete and continuous state Markov Decision Processes
Inference in Markov Decision Processes has recently received interest as a means to infer goals of an observed action, policy recognition, and also as a tool to compute policies. A particularlyExpand
  • 437
  • 21
The 2005 PASCAL Visual Object Classes Challenge
The PASCAL Visual Object Classes Challenge ran from February to March 2005. The goal of the challenge was to recognize objects from a number of visual object classes in realistic scenes (i.e. notExpand
  • 381
  • 21
Probabilistic inference for solving (PO) MDPs
The development of probabilistic inference techniques has made considerable progress in recent years, in particular with respect to exploiting the structure (e.g., factored, hierarchical orExpand
  • 100
  • 17