Fixed Point Theory Analysis of a Lambda Policy Iteration with Randomization for the ¿iri¿ Contraction Operator

• Type: Article in International Conference Proceedings Book
• Date: 2025

Authors

Belhenniche, A (Author) Other; Chertovskih, R (Author) FEUP

Conference proceedings International

Title: Lecture Notes in Electrical Engineering

Pages: 94-105

16th APCA International Conference on Automatic Control and Soft Computing, CONTROLO 2024

Porto, 17 July 2024 through 19 July 2024

Indexing

Scopus - 0 Citations

Other information

Authenticus ID: P-018-NMP

DOI: 10.1007/978-3-031-81724-3_10

Abstract (EN): We apply methods of the fixed point theory to a Lambda policy iteration with a randomization algorithm for weak contractions mappings. This type of mappings covers a broader range than the strong contractions typically considered in the literature, such as ¿iri¿ contraction. Specifically, we explore the characteristics of reinforcement learning procedures developed for feedback control within the context of fixed point theory. Under relatively general assumptions, we identify the sufficient conditions for convergence with a probability of one in infinite-dimensional policy spaces. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 11