Learning optimal control in deterministic systems
| Autor: | Stephan Pareigis |
|---|---|
| Rok vydání: | 1998 |
| Předmět: |
Computer Science::Machine Learning
Mathematical optimization Theoretical computer science Active learning (machine learning) Applied Mathematics Algorithmic learning theory Computational Mechanics Q-learning Multi-task learning Reinforcement learning Markov decision process Instance-based learning Temporal difference learning Mathematics |
| Zdroj: | ZAMM - Journal of Applied Mathematics and Mechanics / Zeitschrift für Angewandte Mathematik und Mechanik. 78:1033-1034 |
| ISSN: | 0044-2267 |
| DOI: | 10.1002/zamm.19980781585 |
| Popis: | Learning algorithms for optimal control problems have similarity with numerical treatment of the Bellman-equation of dynamic programming. The main difference is, that in case of learning the value iteration depends on information from the system, which is not necessarily given in the nodes of a state-space discretization. Two updating-schemes are presented for evaluating the learned information and their applicability is demonstrated on a simple learning problem. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text