Domain Transfer for End-to-end Reinforcement Learning

Domain Transfer for End-to-end Reinforcement Learning

In this master thesis project a LiDAR-based, depth image-based and semantic segmentation image-based reinforcement learning agent is investigated and compared forlearning in simulation and performing in real-time. The project utilize the Deep Deterministic Policy Gradient architecture for learning c...

Full description

Bibliographic Details
Main Authors: Olsson, Anton, Rosberg, Felix
Format: Others
Language:English
Published: Högskolan i Halmstad, Akademin för informationsteknologi 2020
Subjects:
Reinforcement Learning
Domain Transfer
Deep Deterministic Policy Gradient
Reinforcement Learning in Real-time
Computer Sciences
Datavetenskap (datalogi)
Computer Engineering
Datorteknik
Online Access:http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-43042

Internet

http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-43042

Similar Items