Team Formation with Heterogeneous Agents in Computer Games

نویسندگان

  • Robert G. Price
  • Scott D. Goodwin
چکیده

Forming teams using heterogeneous agents that perform well together to accomplish a task in a game can be a challenging problem. There can often be an enormous amount of combinations to look through, and having an agent that is really good at a particular task is no guarantee that agent will perform well on a team with members with different abilities. Picking a good team is important, as changing teams is often not allowed midway through a task. Using Roles to Create Teams Roles can help simplify the search for the best team. As an example, a hockey coach might not put his best six players on the ice, especially if none of his top six players is a goalie. The concept of a goalie simplifies the search since it limits the criteria for the selection of that player to the abilities that are important for someone who is playing in that position. The concept of roles is explained in (Lu 2005), where agents are classified by the capabilities they can offer. To help simplify a selection process, roles will be used to guide search; first the roles that appear in the best teams will be determined, and then best character types to fill those roles will be found. Some character types are more effective than others at certain roles, and some can play more roles than others. The ‘Defender’, ‘Striker’, ‘Leader’, and ‘Controller’ roles (D, S, L, and C) are described in (Schwalb 2009) and explain the roles different characters are best at in the Neverwinter Nights (NWN) game. NWN is a role-playing game, but has also been used as a teaching tool. NWN allows a player to choose from many options when making each character, allowing millions of combinations of unique teams, making it a good tool for this research. The characters have different Copyright © 2010, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. abilities, and based on their strengths we can classify them in different roles. Characters in the ‘Defender’ role are tough and can take a lot of physical damage. ‘Strikers’ are good at dishing out damage, even from a distance. ‘Leaders’ can make their teammates more effective. ‘Controllers’ can damage many enemies simultaneously.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

An Experimental Study of Incentive Reversal in Sequential and Simultaneous Games

I t is commonly held that increasing monetary rewards enhance work effort. This study, however, argues that this will not ineludibly occur in team activities. Incentive Reversal may occur in sequential team productions featuring positive external impacts on agents. This seemingly paradoxical event is explained through two experiments in this article. The first experiment involves a sample ...

متن کامل

Diversity beats strength?: a hands-on experience with 9x9 go

Team formation is a critical step in deploying a multi-agent team. In some scenarios, agents coordinate by voting continuously. When forming such teams, should we focus on the diversity of the team or on the strength of each member? Can a team of diverse (and weak) agents outperform a uniform team of strong agents? In this demo, the user will be able to explore these questions by playing one of...

متن کامل

Diversity Beats Strength? A Hands-on Experience with 9x9 Go (Demonstration)

Team formation is a critical step in deploying a multi-agent team. In some scenarios, agents coordinate by voting continuously. When forming such teams, should we focus on the diversity of the team or on the strength of each member? Can a team of diverse (and weak) agents outperform a uniform team of strong agents? In this demo, the user will be able to explore these questions by playing one of...

متن کامل

An improved particle swarm optimization with a new swap operator for team formation problem

Formation of effective teams of experts has played a crucial role in successful projects especially in social networks. In this paper, a new particle swarm optimization (PSO) algorithm is proposed for solving a team formation optimization problem by minimizing the communication cost among experts. The proposed algorithm is called by improved particle optimization with new swap operator (IPSONSO...

متن کامل

Coordination Approach to Find Best Defense Decision with Multiple Possibilities among Robocup Soccer Simulation Team

In 2D Soccer Simulation league, agents will decide based on information and data in their model. Effective decisions need to have world model information without any noise and missing data; however, there are few solutions to omit noise in world model data; so we should find efficient ways to reduce the effect of noise when making decisions. In this article we evaluate some simple solutions whe...

متن کامل

Hierarchical Functional Concepts for Knowledge Transfer among Reinforcement Learning Agents

This article introduces the notions of functional space and concept as a way of knowledge representation and abstraction for Reinforcement Learning agents. These definitions are used as a tool of knowledge transfer among agents. The agents are assumed to be heterogeneous; they have different state spaces but share a same dynamic, reward and action space. In other words, the agents are assumed t...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2010