skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

Human-level control through deep reinforcement learning

Nature (London), 2015-02, Vol.518 (7540), p.529-533 [Peer Reviewed Journal]

COPYRIGHT 2015 Nature Publishing Group ;COPYRIGHT 2015 Nature Publishing Group ;Copyright Nature Publishing Group Feb 26, 2015 ;ISSN: 0028-0836 ;EISSN: 1476-4687 ;DOI: 10.1038/nature14236 ;PMID: 25719670 ;CODEN: NATUAS

Full text available

Citations Cited by
  • Title:
    Human-level control through deep reinforcement learning
  • Author: Mnih, Volodymyr ; Kavukcuoglu, Koray ; Silver, David ; Rusu, Andrei A ; Veness, Joel ; Bellemare, Marc G ; Graves, Alex ; Riedmiller, Martin ; Fidjeland, Andreas K ; Ostrovski, Georg ; Petersen, Stig ; Beattie, Charles ; Sadik, Amir ; Antonoglou, Ioannis ; King, Helen ; Kumaran, Dharshan ; Wierstra, Daan ; Legg, Shane ; Hassabis, Demis
  • Subjects: Algorithms ; Artificial Intelligence ; Computer & video games ; Humans ; Methods ; Models, Psychological ; Neural networks ; Neural Networks (Computer) ; Physiological aspects ; Psychological aspects ; Reinforcement (Psychology) ; Reinforcement learning (Machine learning) ; Reward ; Video Games
  • Is Part Of: Nature (London), 2015-02, Vol.518 (7540), p.529-533
  • Description: 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 experience to new situations. Remarkably, humans and other animals seem to solve this problem through a harmonious combination of reinforcement learning and hierarchical sensory processing systems, the former evidenced by a wealth of neural data revealing notable parallels between the phasic signals emitted by dopaminergic neurons and temporal difference reinforcement learning algorithms. While reinforcement learning agents have achieved some successes in a variety of domains, their applicability has previously been limited to domains in which useful features can be handcrafted, or to domains with fully observed, low-dimensional state spaces. Here 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. We tested this agent on the challenging domain of classic Atari 2600 games. We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters. This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.
  • Publisher: England: Nature Publishing Group
  • Language: English
  • Identifier: ISSN: 0028-0836
    EISSN: 1476-4687
    DOI: 10.1038/nature14236
    PMID: 25719670
    CODEN: NATUAS
  • Source: ProQuest One Psychology
    AUTh Library subscriptions: ProQuest Central
    MEDLINE
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait