Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model

Nature, pp. 604-609, 2019.

Cited by: 106|Bibtex|Views126|DOI:https://doi.org/10.1038/s41586-020-03051-4
WOS
Other Links: arxiv.org|pubmed.ncbi.nlm.nih.gov

Abstract:

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 environme...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments