日本語
 
Help Privacy Policy ポリシー/免責事項
  詳細検索ブラウズ

アイテム詳細

  Modeling Human Exploration Through Resource-Rational Reinforcement Learning

Binz, M., & Schulz, E. (2023). Modeling Human Exploration Through Resource-Rational Reinforcement Learning. In S., Koyejo, & S., Mohamed (Eds.), Advances in Neural Information Processing Systems 35: 36th Conference on Neural Information Processing Systems (NeurIPS 2022) (pp. 31755-31768). Red Hook, NY, USA: Curran.

Item is

基本情報

表示: 非表示:
アイテムのパーマリンク: https://hdl.handle.net/21.11116/0000-000D-ADFC-5 版のパーマリンク: https://hdl.handle.net/21.11116/0000-000D-ADFD-4
資料種別: 会議論文

ファイル

表示: ファイル

作成者

表示:
非表示:
 作成者:
Binz, M1, 著者                 
Schulz, E1, 著者           
所属:
1Research Group Computational Principles of Intelligence, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_3189356              

内容説明

表示:
非表示:
キーワード: -
 要旨: Equipping artificial agents with useful exploration mechanisms remains a challenge to this day. Humans, on the other hand, seem to manage the trade-off between exploration and exploitation effortlessly. In the present article, we put forward the hypothesis that they accomplish this by making optimal use of limited computational resources. We study this hypothesis by meta-learning reinforcement learning algorithms that sacrifice performance for a shorter description length (defined as the number of bits required to implement the given algorithm). The emerging class of models captures human exploration behavior better than previously considered approaches, such as Boltzmann exploration, upper confidence bound algorithms, and Thompson sampling. We additionally demonstrate that changing the description length in our class of models produces the intended effects: reducing description length captures the behavior of brain-lesioned patients while increasing it mirrors cognitive development during adolescence.

資料詳細

表示:
非表示:
言語:
 日付: 2022-102023-04
 出版の状態: 出版
 ページ: -
 出版情報: -
 目次: -
 査読: -
 識別子(DOI, ISBNなど): -
 学位: -

関連イベント

表示:
非表示:
イベント名: Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022)
開催地: New Orleans, LA, USA
開始日・終了日: 2022-11-28 - 2022-12-09

訴訟

表示:

Project information

表示:

出版物 1

表示:
非表示:
出版物名: Advances in Neural Information Processing Systems 35: 36th Conference on Neural Information Processing Systems (NeurIPS 2022)
種別: 会議論文集
 著者・編者:
Koyejo, S, 編集者
Mohamed, S, 編集者
所属:
-
出版社, 出版地: Red Hook, NY, USA : Curran
ページ: - 巻号: - 通巻号: - 開始・終了ページ: 31755 - 31768 識別子(ISBN, ISSN, DOIなど): ISBN: 9781713871088