Global ETD Search

1	Inovativní směrovací protokoly / Innovative Routing Protocols Rouča, Tomáš January 2012 (has links) The aim of this thesis was to get acquainted with the technology of routing data in a computer network. Thesis described in the theoretical level properties of current and past routing protocols and their use in information systems. Based on the acquired knowledge was created a simulation model of network communication in programming environment OPNET Modeler. This model analyzes the received parameters of the current protocols and their subsequent implementation in the real transmission technology using operating system Debian Linux. Finally, the transfer parameters are discussed between the simulation model and real transfer technology.
2	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
3	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

1

Page generated in 0.0228 seconds