ResearchSpace

Behavioural domain knowledge transfer for autonomous agents

Show simple item record

dc.contributor.author Rosman, Benjamin S
dc.date.accessioned 2015-05-25T10:52:58Z
dc.date.available 2015-05-25T10:52:58Z
dc.date.issued 2014-11
dc.identifier.citation Rosman, B.S. 2014. Behavioural domain knowledge transfer for autonomous agents. Knowledge, Skill, and Behavior Transfer in Autonomous Robots, AAAI 2014 Fall Symposium Series, 13-15 November 2014, pp 1-8 en_US
dc.identifier.uri http://hdl.handle.net/10204/7979
dc.description Knowledge, Skill, and Behavior Transfer in Autonomous Robots, AAAI 2014 Fall Symposium Series, 13-15 November 2014.Due to copyright restrictions, the attached PDF file only contains the abstract of the full text item. For access to the full text item, please consult the publisher's website en_US
dc.description.abstract An agent continuously performing different tasks in the same domain has the opportunity to learn, over the course of its operational lifetime, about the behavioural regularities afforded by the domain. This paper addresses the problem of learning a task independent behaviour model based on the underlying structure of a domain which is common across multiple tasks presented to an autonomous agent. Our approach involves learning action priors: a behavioural model which encodes a notion of local common sense behaviours in the domain, conditioned on either the state or observations of the agent. This knowledge is accumulated and transferred as an exploration behaviour whenever a new task is presented to the agent. The effect is that as the agent encounters more tasks, it is able to learn them faster and achieve greater overall performance. This approach is illustrated in experiments in a simulated extended navigation domain. en_US
dc.language.iso en en_US
dc.publisher Association for the Advancement of Artificial Intelligence en_US
dc.relation.ispartofseries Workflow;13436
dc.subject Autonomous agents en_US
dc.subject Artificial intelligence en_US
dc.subject Behavioural domain knowledge en_US
dc.title Behavioural domain knowledge transfer for autonomous agents en_US
dc.type Conference Presentation en_US
dc.identifier.apacitation Rosman, B. S. (2014). Behavioural domain knowledge transfer for autonomous agents. Association for the Advancement of Artificial Intelligence. http://hdl.handle.net/10204/7979 en_ZA
dc.identifier.chicagocitation Rosman, Benjamin S. "Behavioural domain knowledge transfer for autonomous agents." (2014): http://hdl.handle.net/10204/7979 en_ZA
dc.identifier.vancouvercitation Rosman BS, Behavioural domain knowledge transfer for autonomous agents; Association for the Advancement of Artificial Intelligence; 2014. http://hdl.handle.net/10204/7979 . en_ZA
dc.identifier.ris TY - Conference Presentation AU - Rosman, Benjamin S AB - An agent continuously performing different tasks in the same domain has the opportunity to learn, over the course of its operational lifetime, about the behavioural regularities afforded by the domain. This paper addresses the problem of learning a task independent behaviour model based on the underlying structure of a domain which is common across multiple tasks presented to an autonomous agent. Our approach involves learning action priors: a behavioural model which encodes a notion of local common sense behaviours in the domain, conditioned on either the state or observations of the agent. This knowledge is accumulated and transferred as an exploration behaviour whenever a new task is presented to the agent. The effect is that as the agent encounters more tasks, it is able to learn them faster and achieve greater overall performance. This approach is illustrated in experiments in a simulated extended navigation domain. DA - 2014-11 DB - ResearchSpace DP - CSIR KW - Autonomous agents KW - Artificial intelligence KW - Behavioural domain knowledge LK - https://researchspace.csir.co.za PY - 2014 T1 - Behavioural domain knowledge transfer for autonomous agents TI - Behavioural domain knowledge transfer for autonomous agents UR - http://hdl.handle.net/10204/7979 ER - en_ZA


Files in this item

This item appears in the following Collection(s)

Show simple item record