• Publications
  • Influence
Human-level control through deep reinforcement learning
TLDR
We use recent advances in training deep neural networks to develop a novel artificial agent, termed a deep Q-network, that can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning using the same algorithm, network architecture and hyperparameters. Expand
  • 10,927
  • 1844
  • PDF
Playing Atari with Deep Reinforcement Learning
TLDR
We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning, with no adjustment of the architecture or learning algorithm. Expand
  • 4,567
  • 733
  • PDF
A direct adaptive method for faster backpropagation learning: the RPROP algorithm
TLDR
A learning algorithm for multilayer feedforward networks, RPROP (resilient propagation), is proposed. Expand
  • 4,208
  • 321
  • PDF
Striving for Simplicity: The All Convolutional Net
TLDR
We propose a new architecture that consists solely of convolutional layers and yields competitive or state of the art performance on several object recognition datasets (CIFAR-10, CIFAR100, ImageNet). Expand
  • 2,357
  • 271
  • PDF
Deterministic Policy Gradient Algorithms
TLDR
We introduce an off-policy actor-critic algorithm that learns a deterministic target policy from an exploratory behaviour policy. Expand
  • 1,486
  • 244
  • PDF
Neural Fitted Q Iteration - First Experiences with a Data Efficient Neural Reinforcement Learning Method
TLDR
This paper introduces NFQ, an algorithm for efficient and effective training of a Q-value function represented by a multi-layer perceptron. Expand
  • 734
  • 112
  • PDF
Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images
TLDR
We introduce Embed to Control (E2C), a method for model learning and control of non-linear dynamical systems from raw pixel images. Expand
  • 458
  • 50
  • PDF
Emergence of Locomotion Behaviours in Rich Environments
TLDR
We train agents in diverse environmental contexts, and find that this encourages the emergence of robust behaviours that perform well across a suite of tasks. Expand
  • 460
  • 44
  • PDF
Multimodal deep learning for robust RGB-D object recognition
TLDR
We introduce a novel multimodal neural network architecture for RGB-D object recognition, which achieves state-of-the- art performance on the WashingtonRGB-D Object dataset. Expand
  • 451
  • 40
  • PDF
Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks
TLDR
We show that the feature representation learned by the Exemplar-CNN performs well on two very different tasks: object classification and descriptor matching. Expand
  • 273
  • 39
  • PDF