Human-level control through deep reinforcement learning

  title={Human-level control through deep reinforcement learning},
  author={V. Mnih and K. Kavukcuoglu and D. Silver and Andrei A. Rusu and J. Veness and Marc G. Bellemare and A. Graves and Martin A. Riedmiller and Andreas K. Fidjeland and Georg Ostrovski and S. Petersen and C. Beattie and A. Sadik and Ioannis Antonoglou and H. King and D. Kumaran and Daan Wierstra and S. Legg and Demis Hassabis},
  • V. Mnih, K. Kavukcuoglu, +16 authors Demis Hassabis
  • Published 2015
  • Medicine, Computer Science
  • Nature
  • The theory of reinforcement learning provides a normative account, deeply rooted in psychological and neuroscientific perspectives on animal behaviour, of how agents may optimize their control of an environment. To use reinforcement learning successfully in situations approaching real-world complexity, however, agents are confronted with a difficult task: they must derive efficient representations of the environment from high-dimensional sensory inputs, and use these to generalize past… CONTINUE READING
    Continuous control with deep reinforcement learning
    • 3,528
    • PDF
    Mastering the game of Go with deep neural networks and tree search
    • 7,367
    • PDF
    Asynchronous Methods for Deep Reinforcement Learning
    • 3,300
    • PDF
    Deep Reinforcement Learning with Double Q-Learning
    • 2,027
    • PDF
    Overcoming catastrophic forgetting in neural networks
    • 1,278
    • PDF
    Mastering the game of Go without human knowledge
    • 3,290
    • PDF
    TensorFlow: A system for large-scale machine learning
    • 7,678
    • PDF
    Reinforcement Learning with Unsupervised Auxiliary Tasks
    • 624
    • PDF
    Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
    • 865
    • Highly Influenced
    • PDF
    Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
    • 2,222
    • Highly Influenced
    • PDF


    Publications referenced by this paper.
    Reinforcement Learning: An Introduction
    • 25,498
    • PDF
    Learning Deep Architectures for AI
    • 6,172
    • PDF
    A Neural Substrate of Prediction and Reward
    • 5,914
    • PDF
    Reducing the Dimensionality of Data with Neural Networks
    • 11,149
    • PDF
    Reinforcement learning for robots using neural networks
    • 741
    • PDF