Spelling suggestions: "subject:"bvehavior bnetwork"" "subject:"bvehavior conetwork""
1 |
Structure Learning of a Behavior Network for Context Dependent AdaptabilityLi, Ou 07 December 2006 (has links)
One mechanism for an intelligent agent to adapt to substantial environmental changes is to change its decision making structure. Pervious work in this area has developed a context-dependent behavior selection architecture that uses structure change, i.e., changing the mutual inhibition structures of a behavior network, as the main mechanism to generate different behavior patterns according to different behavioral contexts. Given the important of network structure, this work investigates how the structure of a behavior network can be learned. We developed a structure learning method based on generic algorithm and applied it to a model crayfish that needs to survive in a simulated environment. The model crayfish is controlled by a mutual inhibition behavior network, whose structures are learned using the GA-based algorithm for different environment configurations. The results show that it is possible to learn robust and consistent network structures allowing intelligent agents to behave adaptively in a particular environment.
|
2 |
Artificiella EkosystemSom Artificiell Intelligens I Actionrollspel : En jämförelse av algoritmer och deras anpassning till realtids-spel / Artificial Ecosystems As Artificial Intelligence In Action Role Playing Games : A Comparison Of Algorithms And Their Adaptation To Real Time GamesHärgestam, Olof January 2011 (has links)
Artificiella ekosystem är en tillämpning av artificiell intelligens som har funnits länge. Användningsområden för artificiella ekosystem innefattar främst biologiska simulationer men även andra typer av simulationer förekommer. Genom att simulera individuella djur blir den artificiella intelligensens uppgift att styra djurens beslut utifrån dess individuella förutsättningar och kamp för överlevnad. Detta arbete behandlar frågeställningen vilken beslutsalgoritm som är bäst lämpad att för att använda till ett artificiellt ekosystem i ett spel. Två beslutsalgoritmer jämförs, en dynamisk som bygger på maskin inlärning och en statisk som inte är kapabel att lära eller minnas. Den dynamiska heter Behavior Network och den statiska heter Decision Tree. En applikation byggs för att jämföra hur väl de bägge algoritmerna löser problemet att styra ett artificiellt ekosystem i ett spel. Algoritmerna jämförs efter tre kriterier, svårighet att anpassa till uppgiften, hur mycket beräkningskraft som krävs från datorn att driva algoritmen och hur väl individerna överlever när de styrs av algoritmen. Detta verk visar att Decision Tree är den mer lämpade algoritmen enligt samtliga tre kriterier. Behavior Network visar lovande kvalitéer men inga av resultaten inom ramarna för detta arbete stödjer att använda algoritmen till detta tillämpningsområde.
|
3 |
Distributed virtual environment scalability and securityMiller, John January 2011 (has links)
Distributed virtual environments (DVEs) have been an active area of research and engineering for more than 20 years. The most widely deployed DVEs are network games such as Quake, Halo, and World of Warcraft (WoW), with millions of users and billions of dollars in annual revenue. Deployed DVEs remain expensive centralized implementations despite significant research outlining ways to distribute DVE workloads. This dissertation shows previous DVE research evaluations are inconsistent with deployed DVE needs. Assumptions about avatar movement and proximity - fundamental scale factors - do not match WoW's workload, and likely the workload of other deployed DVEs. Alternate workload models are explored and preliminary conclusions presented. Using realistic workloads it is shown that a fully decentralized DVE cannot be deployed to today's consumers, regardless of its overhead. Residential broadband speeds are improving, and this limitation will eventually disappear. When it does, appropriate security mechanisms will be a fundamental requirement for technology adoption. A trusted auditing system ('Carbon') is presented which has good security, scalability, and resource characteristics for decentralized DVEs. When performing exhaustive auditing, Carbon adds 27% network overhead to a decentralized DVE with a WoW-like workload. This resource consumption can be reduced significantly, depending upon the DVE's risk tolerance. Finally, the Pairwise Random Protocol (PRP) is described. PRP enables adversaries to fairly resolve probabilistic activities, an ability missing from most decentralized DVE security proposals. Thus, this dissertations contribution is to address two of the obstacles for deploying research on decentralized DVE architectures. First, lack of evidence that research results apply to existing DVEs. Second, the lack of security systems combining appropriate security guarantees with acceptable overhead.
|
Page generated in 0.0246 seconds