2026-10-01T22:48:26Zhttps://skemman.is/oai/request

oai:skemman.is:1946/371082025-02-17T09:42:40Zcom_1946_6870com_1946_6001col_1946_34329

Háskólinn í Reykjavík University of Camerino Daniele Marchei 1995- Yngvi Björnsson 1964- Stephan Schiffel 1980- Loreti, Michele Verkefnið er unnið í samvinnu við University of Camerino, Ítalíu. 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. 2020-10-01T09:09:15Z 2020-10-01T09:09:15Z 2020-10-01T09:09:15Z 2020-08-28T17:09:18Z 2020-07 http://hdl.handle.net/1946/37108 en Tölvunarfræði Meistaraprófsritgerðir Tölvuleikir Tauganet Computer science Computer games Neural networks (Computer science) Graph embeddings for deep learning in general game playing Thesis Master's