Stage-oe-small.jpg

Thema4773: Unterschied zwischen den Versionen

Aus Aifbportal
Wechseln zu:Navigation, Suche
(Die Seite wurde neu angelegt: „{{Abschlussarbeit |Titel=Deep Reinforcement Learning for the Control of Robotic Manipulation |Abschlussarbeitstyp=Master |Betreuer=Mohammd Karam Daaboul |Partn…“)
 
 
Zeile 8: Zeile 8:
 
|Beginn=2021/05/04
 
|Beginn=2021/05/04
 
|Ausschreibung=Deep Reinforcement Learning for the Control of Robotic Manipulation.pdf
 
|Ausschreibung=Deep Reinforcement Learning for the Control of Robotic Manipulation.pdf
 +
|Beschreibung DE=Reinforcement Learning (RL) is a method of machine learning in which an agent learns a strategy through interactions with its environment that maximizes the rewards it receives from the environment. The agent is not given a policy but is guided only by positive and negative rewards and optimizes his behavior. In many real-world scenarios, an agent faces the challenges of sparse extrinsic rewards, learning from limited samples,  and no violation of safety constraints.
 +
This thesis aims to research the area of safe RL and develop a method to deal with those three problems.
 
}}
 
}}

Aktuelle Version vom 4. Mai 2021, 10:48 Uhr



Deep Reinforcement Learning for the Control of Robotic Manipulation




Informationen zur Arbeit

Abschlussarbeitstyp: Master
Betreuer: Mohammd Karam Daaboul
Forschungsgruppe: Angewandte Technisch-Kognitive Systeme
Partner: FZI Forschungszentrum Informatik
Archivierungsnummer: 4773
Abschlussarbeitsstatus: Offen
Beginn: 04. Mai 2021
Abgabe: unbekannt

Weitere Informationen

Reinforcement Learning (RL) is a method of machine learning in which an agent learns a strategy through interactions with its environment that maximizes the rewards it receives from the environment. The agent is not given a policy but is guided only by positive and negative rewards and optimizes his behavior. In many real-world scenarios, an agent faces the challenges of sparse extrinsic rewards, learning from limited samples, and no violation of safety constraints. This thesis aims to research the area of safe RL and develop a method to deal with those three problems.


Ausschreibung: Download (pdf)