The RoboCup synthetic agent challenge 97

Kitano, Hiroaki; Tambe, Milind; Stone, Peter; Veloso, Manuela; Coradeschi, Silvia; Osawa, Eiichi; Matsubara, Hitoshi; Noda, Itsuki; Asada, Minoru

doi:10.1007/3-540-64473-3_49

Cited by 170 publications

(94 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…26 The vector quantization technique takes advantage of the statistical characteristics of the domain to reduce its size, considering only relevant areas from the whole domain. The algorithm has been applied to learn the ball interception skill of a goalie, 22 and in cooperative multi-robot observation of multiple moving targets (CMOMMT), 27 to obtain collaborative behaviors in a multirobot observation task.…”

Section: Vqqlmentioning

confidence: 99%

Two steps reinforcement learning

Fernández¹,

Borrajo²

2008

Int. J. Intell. Syst.

View full text Add to dashboard Cite

When applying reinforcement learning in domains with very large or continuous state spaces, the experience obtained by the learning agent in the interaction with the environment must be generalized. The generalization methods are usually based on the approximation of the value functions used to compute the action policy and tackled in two different ways. On the one hand by using an approximation of the value functions based on a supervized learning method. On the other hand, by discretizing the environment to use a tabular representation of the value functions. In this work, we propose an algorithm that uses both approaches to use the benefit of both mechanisms, allowing a higher performance. The approach is based on two learning phases. In the firs one, a learner is used as a supervized function approximator, but using a machine learning technique which also outputs a state space discretization of the environment, such as nearest prototype classifier or decision trees do. In the second learning phase, the space discretization computed in the firs phase is used to obtain a tabular representation of the value function computed in the previous phase, allowing a tuning of such value function approximation. Experiments in different domains show that executing both learning phases improves the results obtained executing only the firs one. The results take into account the resources used and the performance of the learned behavior. C

show abstract

Section: Vqqlmentioning

confidence: 99%

Two steps reinforcement learning

Fernández¹,

Borrajo²

2008

Int. J. Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…An IJCAI-97 challenge paper [8] identified three general research challenges that can be addressed within Soccer Server as being -multiagent learning; -teamwork structures; and -agent/opponent modeling.…”

Section: Projectmentioning

confidence: 99%

RoboCup as an Introduction to CS Research

Stone

2004

RoboCup 2003: Robot Soccer World Cup VII

Self Cite

View full text Add to dashboard Cite

Abstract. This paper proposes using topics central to RoboCup, particularly autonomous agents and multiagent systems, as the subject-matter for a course designed to introduce undergraduate students to all facets of computer science research. Experiences are presented from the design and implementation of such a course. The course is structured around an ongoing incremental programming project that culminates in a class tournament in the RoboCup Soccer Server, an open-source infrastructure built to support multiagent systems research and education.

show abstract

“…The Robot World Cup Initiative (RoboCup) [3] is an international joint project to encourage AI, robotics and related fields. It provides a standard problem where many intelligent techniques must be integrated and examined.…”

Section: Introductionmentioning

confidence: 99%

A Comparing Method of Two Team Behaviours in the Simulation Coach Competition

Iglesias

Ledezma

Sanchís

2006

Modeling Decisions for Artificial Intelligence

View full text Add to dashboard Cite

Abstract. The main goal of agent modelling is to extract and represent the knowledge about the behaviour of other agents. Nowadays, modelling an agent in multi-agent systems is increasingly becoming more complex and significant. Also, robotic soccer domain is an interesting environment where agent modelling can be used. In this paper, we present an approach to classify and compare the behaviour of a multi-agent system using a coach in the soccer simulation domain of the RoboCup.

show abstract

The RoboCup synthetic agent challenge 97

Cited by 170 publications

References 6 publications

Two steps reinforcement learning

Two steps reinforcement learning

RoboCup as an Introduction to CS Research

A Comparing Method of Two Team Behaviours in the Simulation Coach Competition

Contact Info

Product

Resources

About