Conference icon

Conference

Safely interruptible agents

Abstract:
Reinforcement learning agents interacting with a complex environment like the real world are unlikely to behave optimally all the time. If such an agent is operating in real-time under human supervision, now and then it may be necessary for a huma...Expand abstract...
Publication status:
Pubished
Peer review status:
Peer reviewed
Version:
Accepted Manuscript

Actions


Access Document


Files:
Publisher website:
http://auai.org/uai2016/index.php

Authors


More by this author
Institution:
Google DeepMind
More by this author
Institution:
Machine Intelligence Research Institute
Department:
Oxford, HUM, Future of Humanity Insitute
Publisher:
Association for Uncertainty in Artificial Intelligence Publisher's website
Publication date:
2016-05-19
URN:
uuid:17c0e095-4e13-47fc-bace-64ec46134a3f
Source identifiers:
624187
Local pid:
pubs:624187

Terms of use


Stats


Views & Downloads


If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP