Language:

Mastering Atari, Go, chess and shogi by planning with a learned model

Nature (London), 2020-12, Vol.588 (7839), p.604-609 [Peer Reviewed Journal]

COPYRIGHT 2020 Nature Publishing Group ;Copyright Nature Publishing Group Dec 24-Dec 31, 2020 ;ISSN: 0028-0836 ;EISSN: 1476-4687 ;DOI: 10.1038/s41586-020-03051-4 ;PMID: 33361790

Full text available

Citations Cited by

Actions
1. Add to My Research
2. Remove from My Research
3. E-mail
4. Print
5. Permalink
6. Citation
7. EasyBib
8. EndNote
9. RefWorks
10. Delicious
11. Export RIS
12. Export BibTeX

Title:
Mastering Atari, Go, chess and shogi by planning with a learned model
Author: Schrittwieser, Julian ; Antonoglou, Ioannis ; Hubert, Thomas ; Simonyan, Karen ; Sifre, Laurent ; Schmitt, Simon ; Guez, Arthur ; Lockhart, Edward ; Hassabis, Demis ; Graepel, Thore ; Lillicrap, Timothy ; Silver, David
Subjects: Agents (artificial intelligence) ; Algorithms ; Artificial intelligence ; Binary searching ; Chess ; Computer & video games ; Domains ; Expected values ; Games ; Learning ; Mastering ; Neural networks ; Performance evaluation ; Reinforcement ; Reinforcement learning (Machine learning) ; State-of-the-art reviews ; Technology application ; World problems
Is Part Of: Nature (London), 2020-12, Vol.588 (7839), p.604-609
Description: Constructing agents with planning capabilities has long been one of the main challenges in the pursuit of artificial intelligence. Tree-based planning methods have enjoyed huge success in challenging domains, such as chess and Go , where a perfect simulator is available. However, in real-world problems, the dynamics governing the environment are often complex and unknown. Here we present the MuZero algorithm, which, by combining a tree-based search with a learned model, achieves superhuman performance in a range of challenging and visually complex domains, without any knowledge of their underlying dynamics. The MuZero algorithm learns an iterable model that produces predictions relevant to planning: the action-selection policy, the value function and the reward. When evaluated on 57 different Atari games -the canonical video game environment for testing artificial intelligence techniques, in which model-based planning approaches have historically struggled -the MuZero algorithm achieved state-of-the-art performance. When evaluated on Go, chess and shogi-canonical environments for high-performance planning-the MuZero algorithm matched, without any knowledge of the game dynamics, the superhuman performance of the AlphaZero algorithm that was supplied with the rules of the game.
Publisher: England: Nature Publishing Group
Language: English
Identifier: ISSN: 0028-0836
EISSN: 1476-4687
DOI: 10.1038/s41586-020-03051-4
PMID: 33361790
Source: ProQuest One Psychology
ProQuest Central

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	Feedback

Mastering Atari, Go, chess and shogi by planning with a learned model

COPYRIGHT 2020 Nature Publishing Group ;Copyright Nature Publishing Group Dec 24-Dec 31, 2020 ;ISSN: 0028-0836 ;EISSN: 1476-4687 ;DOI: 10.1038/s41586-020-03051-4 ;PMID: 33361790

Searching Remote Databases, Please Wait