Dynamic Abstraction for Hierarchical Problem Solving and Execution in Stochastic Dynamic Environments
2006 (English)In: STAIRS 2006 / [ed] Loris Penserini, Pavlos Peppas, Anna Perini, IOS Press, 2006, Vol. 142, 263-264Conference paper (Refereed)
Most of today’s autonomous problem solving agents perform their task with the help of problem domain specifications that keep their abstractions fixed. Those abstractions are often selected by human users. We think that the approach with fixed-abstraction domain specifications is very inflexible because it does not allow the agent to focus its limited computational resources on what may be most relevant at the moment. We would like to build agents that dynamically find suitable abstractions depending on relevance for their current task and situation. This idea of dynamic abstraction has recently been considered an important research problem within the area of hierarchical reinforcement learning .
Frontiers in Artificial Intelligence and Applications, ISSN 0922-6389 ; 142
National CategoryEngineering and Technology
IdentifiersURN: urn:nbn:se:liu:diva-58465ISI: 000273476500029ISBN: 978-1-58603-645-4ISBN: e-978-1-60750-190-9OAI: oai:DiVA.org:liu-58465DiVA: diva2:343145
3rd Starting Artificial Intelligence Researchers Symposium (STAIRS 2006), 28-29 August 2006, Riva del Garda, Italy