Back to Search Start Over

An Online Policy Gradient Algorithm for Markov Decision Processes with Continuous States and Actions.

Authors :
Yao Ma
Tingting Zhao
Kohei Hatano
Masashi Sugiyama
Source :
Neural Computation. 2016, Vol. 28 Issue 3, p563-593. 31p. 5 Graphs.
Publication Year :
2016

Details

Language :
English
ISSN :
08997667
Volume :
28
Issue :
3
Database :
Academic Search Index
Journal :
Neural Computation
Publication Type :
Academic Journal
Accession number :
113225048
Full Text :
https://doi.org/10.1162/NECO_a_00808