6533b858fe1ef96bd12b6be3

RESEARCH PRODUCT

RDF* Graph Database as Interlingua for the TextWorld Challenge

Didzis GoskoGints BernansGuntis BarzdinsEdgars CelmsPaulis BarzdinsUldis Lavrinovics

subject

InterlinguaInformation retrievalGraph databaseComputer scienceBacktrackingbusiness.industryDeep learningNatural language understandingcomputer.file_formatcomputer.software_genrelanguage.human_languagelanguageReinforcement learningArtificial intelligenceRDFFrameNetbusinesscomputer

description

This paper briefly describes the top-scoring submission to the First TextWorld Problems: A Reinforcement and Language Learning Challenge. To alleviate the partial observability problem, characteristic to the TextWorld games, we split the Agent into two independent components: Observer and Actor, communicating only via the Interlingua of the RDF* graph database. The RDF* graph database serves as the “world model” memory incrementally updated by the Observer via FrameNet informed Natural Language Understanding techniques and is used by the Actor for the efficient exploration and planning of the game Action sequences. We find that the deep-learning approach works best for the Observer component while the Actor policy is better served by backtracking over the set of rules.

yearjournalcountryeditionlanguage
2019-08-012019 IEEE Conference on Games (CoG)
https://doi.org/10.1109/cig.2019.8848012