Title
Toward Meta-level Control of Autonomous Agents.
Abstract
Metareasoning is an important capability for autonomous systems, particularly for those being deployed on long duration missions. An agent with increased self-observation and the ability to control itself in response to changing environments will be more capable in achieving its goals. This is essential for long-duration missions where system designers will not be able to, theoretically or practically, predict all possible problems that the agent may encounter. In this paper we describe preliminary work that integrates the metacognitive architecture MIDCA with an autonomous TREX agent, creating a more self-observable and adaptive agent.
Year
DOI
Venue
2014
10.1016/j.procs.2014.11.107
Procedia Computer Science
Keywords
Field
DocType
Computational metacognition,cognitive architecture,metareasoning,long-duration autonomy
Architecture,Autonomous agent,Computer science,Metacognition,Human–computer interaction,Autonomous system (Internet),Artificial intelligence,Cognitive architecture,Machine learning
Conference
Volume
ISSN
Citations 
41
1877-0509
1
PageRank 
References 
Authors
0.34
5
5
Name
Order
Citations
PageRank
Dustin Dannenhauer1164.55
Michael T. Cox288272.17
Shubham Gupta310.34
Matthew Paisner421.36
Donald Perlis530654.22