Learning as abductive deliberations
Publication Type
Book
Publication Date
1-2006
Abstract
This paper explains an architecture for a BDI agent that can learn based on its own experience. The learning is conducted through explicit procedural knowledge or plans in a goal-directed manner. The learning is described by encoding abductions within the deliberation processes. With this model, the agent is capable of modifying its own plans on the run. We demonstrate that by abducing some complex structures of plan, the agent can also acquire complex structures of knowledge about its interaction with the environment.
Keywords
Plan Body, Belief State, Composite Action, Learn Plan, Deliberation Process
Discipline
Artificial Intelligence and Robotics
First Page
11
Last Page
20
ISBN
9783540366676
Identifier
10.1007/11801603_4
Publisher
Springer Verlag
Citation
SUBAGDJA, Budhitama; Rahwan I.; and Sonenberg L..
Learning as abductive deliberations. (2006). 11-20.
Available at: https://ink.library.smu.edu.sg/sis_research/6921