The Actor-Judge Method: Safe State Exploration for Hierarchical Reinforcement Learning Controllers (AIAA 2018-1634)
AIAA Information Systems-AIAA Infotech@Aerospace (Conference)
2018-01-01
21 pages
Conference paper
English
© Metadata Copyright the British Library Board and other contributors. All rights reserved.
SHERPA: A Safe Exploration Algorithm for Reinforcement Learning Controllers (AIAA 2015-1757)
British Library Conference Proceedings | 2015
|British Library Conference Proceedings | 2017
|Human Demonstrations for Fast and Safe Exploration in Reinforcement Learning (AIAA 2017-1069)
British Library Conference Proceedings | 2017
|