2015
DOI: 10.1155/2015/986262
|View full text |Cite
|
Sign up to set email alerts
|

Abstract: The goal of General Game Playing (GGP) has been to develop computer programs that can perform well across various game types. It is natural for human game players to transfer knowledge from games they already know how to play to other similar games. GGP research attempts to design systems that work well across different game types, including unknown new games. In this review, we present a survey of recent advances (2011 to 2014) in GGP for both traditional games and video games. It is notable that research on … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
18
0

Year Published

2016
2016
2023
2023

Publication Types

Select...
6
2

Relationship

0
8

Authors

Journals

citations
Cited by 33 publications
(18 citation statements)
references
References 47 publications
0
18
0
Order By: Relevance
“…This is a fascinating endeavour in logical reasoning, where all informations about the game (game tactics, game symmetries and so on) are distilled from the set of rules at run time. But, as Swiechowski [9] has pointed out, arising from this tougher task, there are currently a number of limitations or challenges in GGP which are hard to overcome within the GGP-framework:…”
Section: B Related Workmentioning
confidence: 99%
See 2 more Smart Citations
“…This is a fascinating endeavour in logical reasoning, where all informations about the game (game tactics, game symmetries and so on) are distilled from the set of rules at run time. But, as Swiechowski [9] has pointed out, arising from this tougher task, there are currently a number of limitations or challenges in GGP which are hard to overcome within the GGP-framework:…”
Section: B Related Workmentioning
confidence: 99%
“…• Games formulated in GDL have suboptimal performance as a price to pay for its universality: This is because " it is almost impossible, in a general case, to detect what the game is about and which are its crucial, underpinning concepts." [9] • The use of Computational Intelligence (CI), most notably neural networks, deep learning and TD (temporal difference) learning, have not yet had much success in GGP. As Swiechowski [9] writes: " CI-based learning methods are often too slow even with specialized game engines.…”
Section: B Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…Several research platforms currently exist for promoting the development of general AI for games [32], [33]. The most notable examples of this include the General Game Playing (GGP) system [34], which focuses primarily on board and abstract games, the General Video Game AI (GVGAI) framework [35], which focuses on simple video games, and the Arcade Learning Environment [36], [37], which allows agents to play a large number of Atari 2600 games.…”
Section: General Game Platformsmentioning
confidence: 99%
“…These functions usually have to be implemented by human experts for each specific task, thus turning a generalpurpose algorithm such as a state space search into a specific one. For this reason, state-of-the-art general game players [6] usually avoid heuristic functions, relying instead on Monte-Carlo searches to find the values of different states.…”
Section: Introductionmentioning
confidence: 99%