Learning partially observable action schemas

Dafna Shahaf*, Eyal Amir

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

21 Scopus citations

Abstract

We present an algorithm that derives actions' effects and preconditions in partially observable, relational domains. Our algorithm has two unique features: an expressive relational language, and an exact tractable computation. An actionschema language that we present permits learning of preconditions and effects that include implicit objects and unstated relationships between objects. For example, we can learn that replacing a blown fuse turns on all the lights whose switch is set to on. The algorithm maintains and outputs a relational-logical representation of all possible action-schema models after a sequence of executed actions and partial observations. Importantly, our algorithm takes polynomial time in the number of time steps and predicates. Time dependence on other domain parameters varies with the action-schema language. Our experiments show that the relational structure speeds up both learning and generalization, and outperforms prepositional learning methods. It also allows establishing aprioriunknown connections between objects (e.g. light bulbs and their switches), and permits learning conditional effects in realistic and complex situations. Our algorithm takes advantage of a DAG structure that can be updated efficiently and preserves compactness of representation.

Original languageEnglish
Title of host publicationProceedings of the 21st National Conference on Artificial Intelligence and the 18th Innovative Applications of Artificial Intelligence Conference, AAAI-06/IAAI-06
Pages913-919
Number of pages7
StatePublished - 2006
Externally publishedYes
Event21st National Conference on Artificial Intelligence and the 18th Innovative Applications of Artificial Intelligence Conference, AAAI-06/IAAI-06 - Boston, MA, United States
Duration: 16 Jul 200620 Jul 2006

Publication series

NameProceedings of the National Conference on Artificial Intelligence
Volume1

Conference

Conference21st National Conference on Artificial Intelligence and the 18th Innovative Applications of Artificial Intelligence Conference, AAAI-06/IAAI-06
Country/TerritoryUnited States
CityBoston, MA
Period16/07/0620/07/06

Fingerprint

Dive into the research topics of 'Learning partially observable action schemas'. Together they form a unique fingerprint.

Cite this