Distributed Artificial Intelligence (DAI) has existed as a subfield of AI for less than two decades. DAI is

Multi-agent domains consisting of teams of agents that need to collaborate in an adversarial environment offer challenging research opportunities. In this article, we introduce periodic team synchronization (PTS) domains as time-critical environments in which agents act autonomously with low communication, but in which they can periodically synchronize in a full-communication setting. The two main contributions of this article are a flexible team agent structure and a method for inter-agent communication in domains with unreliable, single-channel, low-bandwidth communication. First, the novel team agent structure allows agents to capture and reason about team agreements. We achieve collaboration between agents through the introduction of formations. A formation decomposes the task space defining a set of roles. Homogeneous agents can flexibly switch roles within formations, and agents can change formations dynamically, according to pre-defined triggers to be evaluated at run-time. This flexibility increases the performance of the overall team. Our teamwork structure further includes pre-planning for frequent situations. Second, the novel communication method is designed for use during the lowcommunication periods in PTS domains. It overcomes the obstacles to inter-agent communication in multi-agent environments with unreliable, high-cost, low-bandwidth communication. We fully implemented both the flexible teamwork structure and the communication method in the domain of simulated robotic soccer, and conducted controlled empirical experiments to verify their effectiveness. In addition, our simulator team made it to the semi-finals of the RoboCup-97 competition, in which 29 teams participated.

Vision systems employing region segmentation by color are crucial in real-time mobile robot applications, such as RoboCup[1], or other domains where interaction with humans or a dynamic world is required. Traditionally, systems employing real-time color-based segmentation are either implemented in hardware, or as very specific software systems that take advantage of domain knowledge to attain the necessary efficiency. However, we have found that with careful attention to algorithm efficiency, fast color image segmentation can be accomplished using commodity image capture and CPU hardware. Our paper describes a system capable of tracking several hundred regions of up to 32 colors at 30 Hertz on general purpose commodity hardware. The software system is composed of four main parts; a novel implementation of a threshold classifier, a merging system to form regions through connected components, a separation and sorting system that gathers various region features, and a top down merging heu...

this paper, we investigate a new style for presenting information. We introduce the notion of presentation teams which---rather than addressing the user directly---convey information in the style of performances to be observed by the user. The paper is organized as follows. First, we report on our experience with two single animated presentation agents and explain how to evaluate their success. After that, we move to presentation teams and discuss their potential benefits for presentation tasks. In section 2, we describe the basic steps of our approach to the automated generation of performances with multiple characters. This approach has been applied to two different in: J. Cassell, S. Prevost, J. Sullivan, and E. Churchill: Embodied Conversational

The CMUnited-99 simulator team became the 1999 RoboCup simulator league champion by winning all 8 of its games, outscoring opponents by a combined score of 110--0. CMUnited-99 builds upon the successful CMUnited-98 implementation, but also improves upon it in many ways. This article gives a detailed presentation of CMUnited-99's improvements over CMUnited-98. 1 Introduction The CMUnited robotic soccer project is an ongoing effort concerned with the creation of collaborative and adversarial intelligent agents operating in real-time, dynamic environments. CMUnited teams have been active and successful participants in the international RoboCup (robot soccer world cup) competitions [1, 2, 16]. In particular, the CMUnited-97 simulator team made it to the semi-finals of the first RoboCup competition in Nagoya, Japan [9], the CMUnited-98 simulator team won the second RoboCup competition in Paris, France [14], and the latest CMUnited-99 simulator team won the third RoboCup competition in ...

RoboCup Chollenge offers a set of chollenges for intelligent ogent reseorchers using a friendly competition in a dynomic, reol-time, multiogent domoin. While RoboCup in generol envisions longer ronge chollenges over the next few decodes, RoboCup Chollenge presents three specific chollenges for the next two yeors: (i / learning of individual agents ond teoms; (ii multi-ogent teom plonning ond plan-execution in service of teomwork; ond (iii) opponent mod- eling. RoboCup Chollenge provides o novel opportunity for mochine leorning, plonning, ond multi-ogent reseorchers -- it not only supplies a concrete domain to evolute their techniques, but also challenges researchers to evolve these techniques to face key constraints fundomentol to this domoin: real-time, uncertainty, ond teamwork.

In the past few years, Multiagent Systems (MAS) has emerged as an active subfield of Artificial Intelligence (AI). Because of the inherent complexity of MAS, there is much interest in using Machine Learning (ML) techniques to help build multiagent systems. Robotic soccer is a particularly good domain for studying MAS and Multiagent Learning. Our approach to using ML as a tool for building Soccer Server clients involves layering increasingly complex learned behaviors. In this article, we describe two levels of learned behaviors. First, the clients learn a low-level individual skill that allows them to control the ball effectively. Then, using this learned skill, they learn a higher-level skill that involves multiple players. For both skills, we describe the learning method in detail and report on our extensive empirical testing. We also verify empirically that the learned skills are applicable to game situations.

Multi-agent domains consisting of teams of agents that need to collaborate in an adversarial environment offer challenging research opportunities. In this paper, we introduce periodic team synchronization domains, as time-critical environments in which agents act autonomously with limited communication, but they can periodically synchronize in a full-communication setting. We present a team agent structure that allows for an agent to capture and reason about team agreements. We achieve collaboration between agents through the introduction of formations. A formation decomposes the task space defininga set of roles. Homogeneous agents

In this paper, we investigate a new style for presenting information. We introduce the notion of presentation teams which – rather than addressing the user directly – convey information in the style of performances to be observed by him or her. The paper presents an approach to the automated generation of performances which has been tested in two different application scenarios, car sales dialogues and soccer commentary.

We present a novel multi-agent learning paradigm called team-partitioned, opaque-transition reinforcement learning (TPOT-RL). TPOT-RL introduces the use of action-dependent features...