Number of the records: 1
Balancing Exploitation and Exploration via Fully Probabilistic Design of Decision Policies
- 1.
SYSNO ASEP 0495875 Document Type V - Research Report R&D Document Type The record was not marked in the RIV Title Balancing Exploitation and Exploration via Fully Probabilistic Design of Decision Policies Author(s) Kárný, Miroslav (UTIA-B) RID, ORCID
Hůla, František (UTIA-B)Number of authors 2 Issue data Praha: ÚTIA AV ČR, v.v.i, 2018 Series Research Report Series number 2376 Number of pages 13 s. Publication form Print - P Language eng - English Country CZ - Czech Republic Keywords Exploitation ; Exploration ; Bayesian estimation ; Adaptive systems ; Fully probabilistic design ; Kullback-Leibler divergence ; Decision policy ; Markov decision process Subject RIV BC - Control Systems Theory OECD category Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8) R&D Projects GA16-09848S GA ČR - Czech Science Foundation (CSF) GA18-15970S GA ČR - Czech Science Foundation (CSF) Institutional support UTIA-B - RVO:67985556 Annotation Adaptive decision making learns an environment model serving a design of a decision policy. The policy-generated actions influence both the acquired reward and the future knowledge. The optimal policy properly balances exploitation with exploration. The inherent dimensionality
curse of decision making under incomplete knowledge prevents the realisation of the optimal design.Workplace Institute of Information Theory and Automation Contact Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Year of Publishing 2019
Number of the records: 1