is Íslenska en English

Lokaverkefni (Meistara)

Háskólinn í Reykjavík > Tæknisvið / School of Technology > MSc Tölvunarfræðideild / Department of Computer Science >

Vinsamlegast notið þetta auðkenni þegar þið vitnið til verksins eða tengið í það: http://hdl.handle.net/1946/37108

Titill: 
  • Titill er á ensku Graph embeddings for deep learning in general game playing
Námsstig: 
  • Meistara
Útdráttur: 
  • Útdráttur er á ensku

    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.

Athugasemdir: 
  • Verkefnið er unnið í samvinnu við University of Camerino, Ítalíu.
Samþykkt: 
  • 1.10.2020
URI: 
  • http://hdl.handle.net/1946/37108


Skrár
Skráarnafn Stærð AðgangurLýsingSkráartegund 
Graph Embeddings for Deep Learning in General Game Playing.pdf3.09 MBOpinnHeildartextiPDFSkoða/Opna