Thema4679: Unterschied zwischen den Versionen
Aus Aifbportal
Dh1659 (Diskussion | Beiträge) (Die Seite wurde neu angelegt: „{{Abschlussarbeit |Titel=Efficient Deep Reinforcement Learning by Combining Variational Autoencoders with Soft Actor Critic |Vorname=Moritz |Nachname=Nekolla…“) |
Dh1659 (Diskussion | Beiträge) |
||
Zeile 7: | Zeile 7: | ||
|Partner=FZI | |Partner=FZI | ||
|Forschungsgruppe=Angewandte Technisch-Kognitive Systeme | |Forschungsgruppe=Angewandte Technisch-Kognitive Systeme | ||
− | |Abschlussarbeitsstatus= | + | |Abschlussarbeitsstatus=Abgeschlossen |
|Beginn=2020/08/01 | |Beginn=2020/08/01 | ||
|Beschreibung DE=The objective of this work is to develop and evaluate the power of a Variational Autoencoder (VAE) to enforce Reinforcement Learning (RL) on a wide variety of tasks. This should be enabled by automatically extracting important features from the observation and creating a more dense representation. Applying an RL algorithm on this pre-trained latent space could be more likely to converge. | |Beschreibung DE=The objective of this work is to develop and evaluate the power of a Variational Autoencoder (VAE) to enforce Reinforcement Learning (RL) on a wide variety of tasks. This should be enabled by automatically extracting important features from the observation and creating a more dense representation. Applying an RL algorithm on this pre-trained latent space could be more likely to converge. | ||
}} | }} |
Version vom 26. Oktober 2020, 11:53 Uhr
Efficient Deep Reinforcement Learning by Combining Variational Autoencoders with Soft Actor Critic
Moritz Nekolla
Informationen zur Arbeit
Abschlussarbeitstyp: Bachelor
Betreuer: Mohammd Karam Daaboul
Forschungsgruppe: Angewandte Technisch-Kognitive Systeme
Partner: FZI
Archivierungsnummer: 4679
Abschlussarbeitsstatus: Abgeschlossen
Beginn:
01. August 2020
Abgabe: unbekannt
Weitere Informationen
The objective of this work is to develop and evaluate the power of a Variational Autoencoder (VAE) to enforce Reinforcement Learning (RL) on a wide variety of tasks. This should be enabled by automatically extracting important features from the observation and creating a more dense representation. Applying an RL algorithm on this pre-trained latent space could be more likely to converge.