Global ETD Search

1	Evaluation Functions in General Game Playing Michulke, Daniel 24 July 2012 (has links) (PDF) While in traditional computer game playing agents were designed solely for the purpose of playing one single game, General Game Playing is concerned with agents capable of playing classes of games. Given the game's rules and a few minutes time, the agent is supposed to play any game of the class and eventually win it. Since the game is unknown beforehand, previously optimized data structures or human-provided features are not applicable. Instead, the agent must derive a strategy on its own. One approach to obtain such a strategy is to analyze the game rules and create a state evaluation function that can be subsequently used to direct the agent to promising states in the match. In this thesis we will discuss existing methods and present a general approach on how to construct such an evaluation function. Each topic is discussed in a modular fashion and evaluated along the lines of quality and efficiency, resulting in a strong agent. Agent Spiele Allgemeine Spiele Künstliche Intelligenz Bewertungsfunktionen Zustandsbewertung Heuristik Merkmale Neuronale Netze Neuro-Symbolische Integration Agent Games General Game Playing GGP Artificial Intelligence evaluation function state evaluation heuristic features neural networks neuro-symbolic integration ddc:003 ddc:004 ddc:006 rvk:ST 324 Heuristik Merkmal Agent <Künstliche Intelligenz> Spieltheorie
2	Evaluation Functions in General Game Playing Michulke, Daniel 22 June 2012 (has links) While in traditional computer game playing agents were designed solely for the purpose of playing one single game, General Game Playing is concerned with agents capable of playing classes of games. Given the game's rules and a few minutes time, the agent is supposed to play any game of the class and eventually win it. Since the game is unknown beforehand, previously optimized data structures or human-provided features are not applicable. Instead, the agent must derive a strategy on its own. One approach to obtain such a strategy is to analyze the game rules and create a state evaluation function that can be subsequently used to direct the agent to promising states in the match. In this thesis we will discuss existing methods and present a general approach on how to construct such an evaluation function. Each topic is discussed in a modular fashion and evaluated along the lines of quality and efficiency, resulting in a strong agent.:Introduction Game Playing Evaluation Functions I - Aggregation Evaluation Functions II - Features General Evaluation Related Work Discussion info:eu-repo/classification/ddc/003 ddc:003 info:eu-repo/classification/ddc/004 ddc:004 info:eu-repo/classification/ddc/006 ddc:006

Search results

Evaluation Functions in General Game Playing

Evaluation Functions in General Game Playing