Downloads: 114 | Views: 254 | Weekly Hits: ⮙1 | Monthly Hits: ⮙1

Research Paper | Information Technology | India | Volume 3 Issue 8, August 2014 | Popularity: 7.1 / 10

Rate This Article!      

Efficient Intelligent Virtual Agents for Developing Game Application Using PRS Engine

Shanthi. P, Maheswari. P

Abstract: complex tasks that require much knowledge, it is necessary to employ several software agents. These agents need to share their knowledge among themselves. Sometimes the results of applying this knowledge together may fail. There are systems which tend to work without intervention from humans and are self-organizing systems. There is a need for intelligent system for any Multiagent application in the real world. But many real world systems related to multi agent scenario fails in the decision making. Combining artificial intelligence (AI) with a graphical representation, virtual agents are increasingly used in CRM (customer relationship management) to help people perform tasks such as locating information or placing orders and making reservations but fails in the performance related to some interaction and concentration factors. In the research, the system has been modeled by developing a theory of mind for gaming applications using PRS (procedural reasoning system) with better reasoning to the agent with extended capabilities. The behavior of the agents has been carried out by comparing the proposed solution with other familiar virtual agent system based upon certain criteria. Some tasks can be broken into sub-tasks to be performed independently by specialized agents. Such agents work independently in their environments and complete all their operations successfully. The multiple agents interact with each other to share information or barter for specialized services to affect a deliberate synergism. Decision tree learning algorithm has been successfully used in expert systems in capturing knowledge. The main task performed in these systems is using inductive methods to the given values of attributes of an unknown object to determine appropriate classification according to decision tree rules. In decision tree learning, ID3 (Iterative Dichotomiser 3) is an algorithm used to generate a decision tree from SUDOKU game data set. ID3 is typically used in the machine learning and natural language processing domains. The main advantages of the ID3 algorithm are that it is easily implemented, being quite a simple process, and its running time increases only linearly with the complexity of the problem. Procedural Reasoning System (PRS) is a framework for constructing real-time reasoning systems that can perform complex tasks in dynamic environments. It is based on the notion of a rational agent or intelligent agent using the BeliefDesireIntention (BDI) software model. Each knowledge area provided to the Procedural Reasoning System is a piece of procedural knowledge that specifies how to do something. The last Non player charactertics agent uses a Theory of mind approach and explicitly uses a BDI model it has of the player. Procedural Reasoning System combined with a theory of mind approach allows the Non player charactertics agent to reason about the BDI model of the player and manipulate the player (i. e. , the players observations) in such manner that the player no longer performs actions that ultimately lead to winning the game.

Keywords: Agent, Multiagent, decision making, dynamic information,

Edition: Volume 3 Issue 8, August 2014

Pages: 1127 - 1130

Make Sure to Disable the Pop-Up Blocker of Web Browser

Click to Cite this Article