English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

General Game Playing (GGP) is a framework in which an artificial intelligenceprogram is required to play a variety of games successfully. It acts as a testbed for AI and motivator of research. The AI is given a random game descriptionat runtime which it then plays. The framework includes repositories of gamerules. The Inductive General Game Playing (IGGP) problem challenges machinelearning systems to learn these GGP game rules by watching the game beingplayed. In other words, IGGP is the problem of inducing general game rules fromspecific game observations. Inductive Logic Programming (ILP) has shown to be apromising approach to this problem though it has been demonstrated that it isstill a hard problem for ILP systems. Existing work on IGGP has always assumedthat the game player being observed makes random moves. This is notrepresentative of how a human learns to play a game. With random gameplaysituations that would normally be encountered when humans play are not present.To address this limitation, we analyse the effect of using intelligent versusrandom gameplay traces as well as the effect of varying the number of traces inthe training set. We use Sancho, the 2014 GGP competition winner, to generateintelligent game traces for a large number of games. We then use the ILPsystems, Metagol, Aleph and ILASP to induce game rules from the traces. Wetrain and test the systems on combinations of intelligent and random dataincluding a mixture of both. We also vary the volume of training data. Ourresults show that whilst some games were learned more effectively in some ofthe experiments than others no overall trend was statistically significant. Theimplications of this work are that varying the quality of training data asdescribed in this paper has strong effects on the accuracy of the learned gamerules; however one solution does not work for all games.

Inducing game rules from varying quality game play