Reinforcement Learning with Orthonormal Basis Adaptation Based on Activity-Oriented Index Allocation

• SATOH Hideki

  Future University-Hakodate The Institute of Electronics, Information and Communication Engineers

抄録

An orthonormal basis adaptation method for function approximation was developed and applied to reinforcement learning with multi-dimensional continuous state space. First, a basis used for linear function approximation of a control function is set to an orthonormal basis. Next, basis elements with small activities are replaced with other candidate elements as learning progresses. As this replacement is repeated, the number of basis elements with large activities increases. Example chaos control problems for multiple logistic maps were solved, demonstrating that the method for adapting an orthonormal basis can modify a basis while holding the orthonormality in accordance with changes in the environment to improve the performance of reinforcement learning and to eliminate the adverse effects of redundant noisy states.

収録刊行物

• IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

  IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E91-A (4), 1169-1176, 2008

  一般社団法人 電子情報通信学会

キーワード

• orthonormal basis
• function approximation
• non-linear
• reinforcement learning
• activity

詳細情報

• CRID: 1390282681287777664
• NII論文ID: 10026848823
• NII書誌ID: AA10826239
• DOI: 10.1093/ietfec/e91-a.4.1169
• ISSN: 17451337
• ISSN: 09168508
• HANDLE: 10445/2361
• Web Site: https://fun.repo.nii.ac.jp/records/998
• Web Site: https://www.jstage.jst.go.jp/article/transfun/E91.A/4/E91.A_4_1169/_pdf
• 本文言語コード: en
• データソース種別:
  • JaLC
  • IRDB
  • Crossref
  • CiNii Articles
• 抄録ライセンスフラグ: 使用不可