A profit sharing reinforcement learning method using hierarchical reward propagation function based on action history

Z.Gong, H.Nakano, A.Miyauchi, Hidehiro NAKANO

研究成果: ジャーナルへの寄稿 › Misc

寄稿の翻訳タイトル	A profit sharing reinforcement learning method using hierarchical reward propagation function based on action history
本文言語	Japanese
ページ（範囲）	293 - 298
ジャーナル	IEICE Technical report
巻	Vol.113
号	No.500
出版ステータス	出版済み - 2014

引用スタイル

@article{ba3108cb0bdc43ecb528c5a889902de3,

title = "A profit sharing reinforcement learning method using hierarchical reward propagation function based on action history",

author = "Z.Gong and H.Nakano and A.Miyauchi and Hidehiro NAKANO",

year = "2014",

language = "Japanese",

volume = "Vol.113",

pages = "293 -- 298",

journal = "IEICE Technical report",

publisher = "電子情報通信学会",

number = "No.500",

}