Stage-oe-small.jpg

Thema4568

Aus Aifbportal
Version vom 10. März 2020, 15:19 Uhr von Dh1659 (Diskussion | Beiträge) (Die Seite wurde neu angelegt: „{{Abschlussarbeit |Titel=Constrained Model-Based Policy Optimization for Real World Applications |Vorname=Moritz |Nachname=Zanger |Abschlussarbeitstyp=Master |…“)
(Unterschied) ← Nächstältere Version | Aktuelle Version (Unterschied) | Nächstjüngere Version → (Unterschied)
Wechseln zu:Navigation, Suche



Constrained Model-Based Policy Optimization for Real World Applications




Informationen zur Arbeit

Abschlussarbeitstyp: Master
Betreuer: Mohammd Karam Daaboul
Forschungsgruppe: Angewandte Technisch-Kognitive Systeme
Partner: FZI Forschungszentrum Informatik
Archivierungsnummer: 4568
Abschlussarbeitsstatus: In Bearbeitung
Beginn: 30. März 2020
Abgabe: unbekannt

Weitere Informationen

Safety and sample efficiency are among the most urgent challenges faced by real-world applications of current reinforcement learning algorithms. Recent developments in model-based reinforcement learning have made significant progress in both sample efficiency and asymptotic performance which is often associated with the model bias problem. The overall goal of this thesis is to derive a sample efficient, safe policy search algorithm by leveraging recent results in model-based reinforcement learning and safety-driven reinforcement algorithms. The combination of model-based methods with safety-driven approaches is motivated by the notion that the agent can safely explore and improve within model rollouts, thus reducing the total needed amount of risky real domain interactions.