Open AccessReinforcement Learning for POMDP Environments Using State Representation with Reservoir Computing
Author(s) -
Kodai Yamashita,
Tomoki Hamagami
Publication year - 2022
Publication title -
journal of advanced computational intelligence and intelligent informatics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.172
H-Index - 20
eISSN - 1343-0130
pISSN - 1883-8014
DOI - 10.20965/jaciii.2022.p0562
Subject(s) - partially observable markov decision process , reinforcement learning , computer science , reservoir computing , artificial intelligence , dual (grammatical number) , markov decision process , perfect information , state (computer science) , representation (politics) , observable , markov process , series (stratigraphy) , process (computing) , machine learning , markov chain , markov model , algorithm , artificial neural network , recurrent neural network , mathematics , art , mathematical economics , law , literature , operating system , political science , statistics , politics , biology , paleontology , quantum mechanics , physics