Abstract
Controlling complex dynamic systems requires skills that operators often cannot completely describe but can demonstrate. Behavioural cloning is the process of reconstructing a skill from an operator’s behavioural traces by means of Machine Learning techniques. In this paper we analyse various phenomena and problems observed in experiments in behavioural cloning in several domains: piloting, driving a container crane, production scheduling and pole-balancing. The analysis includes the “clean-up” effect and the time delay between state and action. We derive from this analysis some elements of an emerging methodology for behavioural cloning.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.