Skip to Main content Skip to Navigation
Conference papers

A Short-Term Memory for Deliberative Agents in Everyday Environments

Abstract : Humans have the impressive capability to efficiently find near-optimal solutions to complex, multi-step problems. AI planning can model such problems well, but is inefficient for realistic problems. We propose to use AI planning in combination with a short-term memory, inspired by models of human short-term memory, to structure real-world problem domains and make the planning process more efficient, while still producing satisficing solutions. We evaluate the method in the domain of a household robot.
Complete list of metadatas

Cited literature [25 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01693669
Contributor : Alexandra Kirsch <>
Submitted on : Friday, January 26, 2018 - 2:15:07 PM
Last modification on : Monday, January 29, 2018 - 1:39:42 PM
Document(s) archivé(s) le : Friday, May 25, 2018 - 4:57:07 AM

File

chichkov16shortterm-preprint.p...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01693669, version 1

Citation

Ivo Chichkov, Alexandra Kirsch. A Short-Term Memory for Deliberative Agents in Everyday Environments. 2nd Global Conference on Artificial Intelligence (GCAI), 2016, Berlin, Germany. ⟨hal-01693669⟩

Share

Metrics

Record views

98

Files downloads

209