Presentation 2023-11-27
Improving the reproduction of animal intelligence using reinforcement learning with World Model
Takumi Fukaya, Hirokazu Tanaka,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) One way to evaluate artificial intelligence models that reproduce animal intelligence is to have reinforcement learning agents perform tasks in a virtual environment. In this talk, we will use the World Model, a deep reinforcement learning method, and propose to reproduce specific tasks in animal intelligence using a reinforcement learning agent. As an example, we will compare the performance with conventional methods when learning a radial maze.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Artificial Intelligence / reinforcement learning / animal intelligence / World Models
Paper # NC2023-34
Date of Issue 2023-11-20 (NC)

Conference Information
Committee NC / MBE
Conference Date 2023/11/27(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Kindai Univ.
Topics (in Japanese) (See Japanese page)
Topics (in English) Brain Architecture, NC, ME
Chair Hirokazu Tanaka(Tokyo City Univ.) / Hisashi Yoshida(Kinki Univ.)
Vice Chair Jun Izawa(Univ. of Tsukub) / Akinori Ueno(Tokyo Denki Univ.)
Secretary Jun Izawa(NTT) / Akinori Ueno(NAIST)
Assistant Yoshimasa Tawatsuji(Waseda Univ.) / Takato Horii(Osaka Univ.) / Akihiko Tsukahara(Tokyo Denki Univ.) / Miki Kaneko(Osaka Univ.)

Paper Information
Registration To Technical Committee on Neurocomputing / Technical Committee on ME and Bio Cybernetics
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Improving the reproduction of animal intelligence using reinforcement learning with World Model
Sub Title (in English)
Keyword(1) Artificial Intelligence
Keyword(2) reinforcement learning
Keyword(3) animal intelligence
Keyword(4) World Models
1st Author's Name Takumi Fukaya
1st Author's Affiliation Tokyo City University(Tokyo City Univ.)
2nd Author's Name Hirokazu Tanaka
2nd Author's Affiliation Tokyo City University(Tokyo City Univ.)
Date 2023-11-27
Paper # NC2023-34
Volume (vol) vol.123
Number (no) NC-285
Page pp.pp.6-9(NC),
#Pages 4
Date of Issue 2023-11-20 (NC)