An Automatically Generated Evaluation Function in General Game Playing

Walędzik, Karol; Mańdziuk, Jacek

doi:10.1109/tciaig.2013.2286825

Cited by 42 publications

(21 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general game playing (GGP) research based on the Stanford game definition language (GDL) [11], various approaches have been proposed for using general game features [12]- [16]. These are all built around the logic-based formalism of GDL, and therefore not directly applicable to general game systems that use a different language (such as LUDII).…”

Section: B Specification Of Featuresmentioning

confidence: 99%

Biasing MCTS with Features for General Games

Soemers

Piette

Browne

2019

2019 IEEE Congress on Evolutionary Computation (CEC)

View full text Add to dashboard Cite

This paper proposes using a linear function approximator, rather than a deep neural network (DNN), to bias a Monte Carlo tree search (MCTS) player for general games. This is unlikely to match the potential raw playing strength of DNNs, but has advantages in terms of generality, interpretability and resources (time and hardware) required for training. Features describing local patterns are used as inputs. The features are formulated in such a way that they are easily interpretable and applicable to a wide range of general games, and might encode simple local strategies. We gradually create new features during the same self-play training process used to learn feature weights. We evaluate the playing strength of an MCTS player biased by learnt features against a standard upper confidence bounds for trees (UCT) player in multiple different board games, and demonstrate significantly improved playing strength in the majority of them after a small number of self-play training games.

show abstract

Section: B Specification Of Featuresmentioning

confidence: 99%

Biasing MCTS with Features for General Games

Soemers

Piette

Browne

2019

2019 IEEE Congress on Evolutionary Computation (CEC)

View full text Add to dashboard Cite

show abstract

“…Similarly Firefly Algorithm application was proposed by Woźniak and Marszałek [13]. Walendzik et al reported development in gaming technologies for automatically generated evaluation [14] and Swiechowski et al discussed self adapting strategies to gaming reality [15]. Decision making systems widely use adaptive strategies to simulate intelligent data streaming processing as reported by Rutkowski et al [16].…”

Section: A Related Workmentioning

confidence: 99%

Toward adaptive heuristic video frames capturing and correction in real-time

Woźniak

Połap

Capizzi

et al. 2016

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

Abstract-Multimedia devices are widely used in professional applications as well as personal purposes. The use of computer vision systems enables detection and extraction of important features exposed in images. However constantly increasing demand for this type of video with high quality requires simple however reliable methods. The objective of presented research is to investigate applicability of heuristic method for real-time video frames capturing and correction.

show abstract

“…CadiaPlayer [16], are simulation based. Also the GGP players currently developed by the authors [17], [18] as well as their previous player [19] are simulation-based agents. A tailor-made interpreter, when properly implemented, can reach a better speed performance than Prolog.…”

Section: Motivationmentioning

confidence: 99%

Prolog versus specialized logic inference engine in General Game Playing

Mańdziuk

2014

2014 IEEE Conference on Computational Intelligence and Games

Self Cite

View full text Add to dashboard Cite

In this paper, we study the problem of applying an inference engine, i.e. a mechanism able to derive answers from a knowledge base, to General Game Playing (GGP). Our focus is on the General Game Playing Competition framework proposed by the Stanford Logic Group. This particular embodiment of a multi-game playing uses the Game Description Language (GDL) for representing the knowledge base by means of game rules.The GDL is a variant of Datalog and a subset of Prolog, so there is a strong bond with formal logic languages. We present basic principles of our system which is dedicated to GDL. The motivation is to exceed the performance of Prolog engines applied to GDL, which is currently a common approach. Empirical results show that our solution is indeed faster in 6 out of 7 tested games.

show abstract

An Automatically Generated Evaluation Function in General Game Playing

Cited by 42 publications

References 18 publications

Biasing MCTS with Features for General Games

Biasing MCTS with Features for General Games

Toward adaptive heuristic video frames capturing and correction in real-time

Prolog versus specialized logic inference engine in General Game Playing

Contact Info

Product

Resources

About