{"id":{"repo_id":"reykjavik","oai_identifier":"oai:skemman.is:1946/37108"},"canonical_url":"https://search.dev.ndltd.org/etd/reykjavik/oai:skemman.is:1946/37108","repository":{"repo_id":"reykjavik","name":"Reykjavík University","base_url":"https://skemman.is/oai/request"},"display":{"title":"Graph embeddings for deep learning in general game playing","abstract":"General Game Playing agents can play many different games. They take as an input a description of a game written in a Game Description Language (GDL) and then infer a proper strategy for playing that game. Typically this includes learning a value function for evaluating the merit of game states, for example, by using a neural network. In this work we investigate whether more effective neural networks-based state evaluations can be built by feeding the networks not only with positions describing the game states but also a graph-based embedding of the game rules (derived from GDL). The game rules are encoded as either Rule Graphs or Propositional Networks, and then we experiment with several different graph-based embeddings for encoding the graphs. The result shows that such an approach has promise, but care must be taken in choosing an appropriate embedding.","abstract_html":"General Game Playing agents can play many different games. They take as an input a description of a game written in a Game Description Language (GDL) and then infer a proper strategy for playing that game. Typically this includes learning a value function for evaluating the merit of game states, for example, by using a neural network. In this work we investigate whether more effective neural networks-based state evaluations can be built by feeding the networks not only with positions describing the game states but also a graph-based embedding of the game rules (derived from GDL). The game rules are encoded as either Rule Graphs or Propositional Networks, and then we experiment with several different graph-based embeddings for encoding the graphs. The result shows that such an approach has promise, but care must be taken in choosing an appropriate embedding.","abstract_has_math":false,"creators":["Daniele Marchei 1995-"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Háskólinn í Reykjavík","University of Camerino"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-10-01T09:09:15Z","date_published":"2020-10-01T09:09:15Z","updated_at":"2026-07-27T20:40:29Z","subjects":["Tölvunarfræði","Meistaraprófsritgerðir","Tölvuleikir","Tauganet","Computer science","Computer games","Neural networks (Computer science)"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1946/37108","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Háskólinn í Reykjavík","University of Camerino"]},{"key":"dc:creator","label":"Author","values":["Daniele Marchei 1995-"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2020-10-01T09:09:15Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2020-10-01T09:09:15Z"]},{"key":"dc:date.issued","label":"Date","values":["2020-10-01T09:09:15Z"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Tölvunarfræði","Meistaraprófsritgerðir","Tölvuleikir","Tauganet","Computer science","Computer games","Neural networks (Computer science)"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1946/37108"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Verkefnið er unnið í samvinnu við University of Camerino, Ítalíu."]},{"key":"dc:description.abstract","label":"Abstract","values":["General Game Playing agents can play many different games. They take as an input a description of a game written in a Game Description Language (GDL) and then infer a proper strategy for playing that game. Typically this includes learning a value function for evaluating the merit of game states, for example, by using a neural network. In this work we investigate whether more effective neural networks-based state evaluations can be built by feeding the networks not only with positions describing the game states but also a graph-based embedding of the game rules (derived from GDL). The game rules are encoded as either Rule Graphs or Propositional Networks, and then we experiment with several different graph-based embeddings for encoding the graphs. The result shows that such an approach has promise, but care must be taken in choosing an appropriate embedding."]},{"key":"dc:title","label":"Title","values":["Graph embeddings for deep learning in general game playing"]}]}],"canonical_facts":{"dc:contributor":["Háskólinn í Reykjavík","University of Camerino"],"dc:creator":["Daniele Marchei 1995-"],"dc:date.accessioned":["2020-10-01T09:09:15Z"],"dc:date.available":["2020-10-01T09:09:15Z"],"dc:date.issued":["2020-10-01T09:09:15Z"],"dc:description":["Verkefnið er unnið í samvinnu við University of Camerino, Ítalíu."],"dc:description.abstract":["General Game Playing agents can play many different games. They take as an input a description of a game written in a Game Description Language (GDL) and then infer a proper strategy for playing that game. Typically this includes learning a value function for evaluating the merit of game states, for example, by using a neural network. In this work we investigate whether more effective neural networks-based state evaluations can be built by feeding the networks not only with positions describing the game states but also a graph-based embedding of the game rules (derived from GDL). The game rules are encoded as either Rule Graphs or Propositional Networks, and then we experiment with several different graph-based embeddings for encoding the graphs. The result shows that such an approach has promise, but care must be taken in choosing an appropriate embedding."],"dc:identifier.uri":["http://hdl.handle.net/1946/37108"],"dc:language.iso":["en"],"dc:subject":["Tölvunarfræði","Meistaraprófsritgerðir","Tölvuleikir","Tauganet","Computer science","Computer games","Neural networks (Computer science)"],"dc:title":["Graph embeddings for deep learning in general game playing"],"dc:type":["Thesis"]},"updated_at":"2026-07-27T20:40:29Z"}