Learning to Fly with a Video Generator

Chia Chun Chung, Wen Hsiao Peng, Teng Hu Cheng, Chia Hau Yu

研究成果: Conference contribution同行評審

摘要

This paper demonstrates a model-based reinforcement learning framework for training a self-flying drone. We implement the Dreamer proposed in a prior work as an environment model that responds to the action taken by the drone by predicting the next video frame as a new state signal. The Dreamer is a conditional video sequence generator. This model-based environment avoids the time-consuming interactions between the agent and the environment, speeding up largely the training process. This demonstration showcases for the first time the application of the Dreamer to train an agent that can finish the racing task in the Airsim simulator.

原文English
主出版物標題2021 International Conference on Visual Communications and Image Processing, VCIP 2021 - Proceedings
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781728185514
DOIs
出版狀態Published - 2021
事件2021 International Conference on Visual Communications and Image Processing, VCIP 2021 - Munich, 德國
持續時間: 5 12月 20218 12月 2021

出版系列

名字2021 International Conference on Visual Communications and Image Processing, VCIP 2021 - Proceedings

Conference

Conference2021 International Conference on Visual Communications and Image Processing, VCIP 2021
國家/地區德國
城市Munich
期間5/12/218/12/21

指紋

深入研究「Learning to Fly with a Video Generator」主題。共同形成了獨特的指紋。

引用此