Distributed Artificial Intelligence (DAI) has existed as a subfield of AI for less than two decades. DAI is concerned with systems that consist of multiple independent entities that interact in a domain. Traditionally, DAI has been divided into two sub-disciplines: Distributed Problem Solving (DPS) focuses on the information management aspects of systems with several components working together towards a common goals Multiagent Systems (MAS) deals with behavior management in collections of several independent entities, or agents. This survey of MAS is intended to serve as an introduction to the field and as an organizational framework. A series of general multiagent scenarios are presented. For each scenario, the issues that arise are described along with a sampling of the techniques that exist to deal with them. The presented techniques are not exhaustive, but they highlight how multiagent systems can be and have been used to build complex systems. When options exist, the techniques presented are biased towards machine learning approaches. Additional opportunities for applying machine learning to MAS are highlighted and robotic soccer is presented as an appropriate test bed for MAS. This survey does not focus exclusively on robotic systems. However, we believe that much of the prior research in non-robotic MAS is relevant to robotic MAS, and we explicitly discuss several robotic MAS, including all of those presented in this issue.

/pdf/multiagent-systems-a-survey-from-a-machine-learning-yps633tity.pdf

Multiagent Systems: A Survey from a Machine Learning Perspective

RoboCup simulated soccer presents many challenges to reinforcement learning methods, including a large state space, hidden and uncertain state, multiple independent agents learning simultaneously, and long and variable delays in the effects of actions. We describe our application of episodic SMDP Sarsa(λ) with linear tile-coding function approximation and variable λ to learning higher-level decisions in a keepaway subtask of RoboCup soccer. In keepaway, one team, “the keepers,” tries to keep control of the ball for as long as possible despite the efforts of “the takers.” The keepers learn individually when to hold the ball and when to pass to a teammate. Our agents learned policies that significantly outperform a range of benchmark policies. We demonstrate the generality of our approach by applying it to a number of task variations including different field sizes and different numbers of players on each team.

/pdf/reinforcement-learning-for-robocup-soccer-keepaway-ku565uhymb.pdf

Reinforcement learning for RoboCup soccer keepaway

Batch reinforcement learning methods provide a powerful framework for learning efficiently and effectively in autonomous robots. The paper reviews some recent work of the authors aiming at the successful application of reinforcement learning in a challenging and complex domain. It discusses several variants of the general batch learning framework, particularly tailored to the use of multilayer perceptrons to approximate value functions over continuous state spaces. The batch learning framework is successfully used to learn crucial skills in our soccer-playing robots participating in the RoboCup competitions. This is demonstrated on three different case studies.

/pdf/reinforcement-learning-for-robot-soccer-xc27gxtqaw.pdf

Reinforcement learning for robot soccer

Multi-agent systems in complex, real-time domains require agents to act effectively both autonomously and as part of a team. This dissertation addresses multi-agent systems consisting of teams of autonomous agents acting in real-time, noisy, collaborative, and adversarial environments. Because of the inherent complexity of this type of multi-agent system, this thesis investigates the use of machine learning within multi-agent systems. The dissertation makes four main contributions to the fields of Machine Learning and Multi-Agent Systems. 
First, the thesis defines a team member agent architecture within which a flexible team structure is presented, allowing agents to decompose the task space into flexible roles and allowing them to smoothly switch roles while acting. Team organization is achieved by the introduction of a locker-room agreement as a collection of conventions followed by all team members. It defines agent roles, team formations, and pre-compiled multi-agent plans. In addition, the team member agent architecture includes a communication paradigm for domains with single-channel, low-bandwidth, unreliable communication. The communication paradigm facilitates team coordination while being robust to lost messages and active interference from opponents. 
Second, the thesis introduces layered learning, a general-purpose machine learning paradigm for complex domains in which learning a mapping directly from agents' sensors to their actuators is intractable. Given a hierarchical task decomposition, layered learning allows for learning at each level of the hierarchy, with learning at each level directly affecting learning at the next higher level. 
Third, the thesis introduces a new multi-agent reinforcement learning algorithm, namely team-partitioned, opaque-transition reinforcement learning (TPOT-RL). TPOT-RL is designed for domains in which agents cannot necessarily observe the state changes when other team members act. It exploits local, action-dependent features to aggressively generalize its input representation for learning and partitions the task among the agents, allowing them to simultaneously learn collaborative policies by observing the long-term effects of their actions. 
Fourth, the thesis contributes a fully functioning multi-agent system that incorporates learning in a real-time, noisy domain with teammates and adversaries. Detailed algorithmic descriptions of the agents' behaviors as well as their source code are included in the thesis. 
Empirical results validate all four contributions within the simulated robotic soccer domain. The generality of the contributions is verified by applying them to the real robotic soccer, and network routing domains. Ultimately, this dissertation demonstrates that by learning portions of their cognitive processes, selectively communicating, and coordinating their behaviors via common knowledge, a group of independent agents can work towards a common goal in a complex, real-time, noisy, collaborative, and adversarial environment.

Layered learning in multiagent systems

Temporal difference (TD) learning (Sutton and Barto, 1998) has become a popular reinforcement learning technique in recent years. TD methods, relying on function approximators to generalize learning to novel situations, have had some experimental successes and have been shown to exhibit some desirable properties in theory, but the most basic algorithms have often been found slow in practice. This empirical result has motivated the development of many methods that speed up reinforcement learning by modifying a task for the learner or helping the learner better generalize to novel situations. This article focuses on generalizing across tasks, thereby speeding up learning, via a novel form of transfer using handcoded task relationships. We compare learning on a complex task with three function approximators, a cerebellar model arithmetic computer (CMAC), an artificial neural network (ANN), and a radial basis function (RBF), and empirically demonstrate that directly transferring the action-value function can lead to a dramatic speedup in learning with all three. Using transfer via inter-task mapping (TVITM), agents are able to learn one task and then markedly reduce the time it takes to learn a more complex task. Our algorithms are fully implemented and tested in the RoboCup soccer Keepaway domain.

This article contains and extends material published in two conference papers (Taylor and Stone, 2005; Taylor et al., 2005).

/pdf/transfer-learning-via-inter-task-mappings-for-temporal-3gurnbdvwh.pdf

Transfer Learning via Inter-Task Mappings for Temporal Difference Learning

This article describes Soccer Server, a simulator of the game of soccer designed as a benchmark for evaluating multiagent systems and cooperative algorithms. In real life, successful soccer teams require many qualities, such as basic ball control skills, the ability to carry out strategies, and teamwork. We believe that simulating such behaviors is a significant challenge for computer science, artificial intelligence, and robotics technologies. It is to promote the development of such technologies, and to help define a new standard problem for research, that we have developed Soccer Server. We demonstrate the potential of Soccer Server by reporting an experiment that uses the system to compare the performance of a neural network architecture and a decision tree algorithm at learning the selection of soccer play plans. Other researchers using Soccer Server to investigate the nature of cooperative behavior in a multiagent environment will have the chance to assess their progress at RoboCup-97, an internatio...

Soccer server: A tool for research on multiagent systems

We have built a multiple autonomous-robots simulator in order to study cooperative learning ’of multiagent systems. By using the simulator, experiments can be done for any tasks by any learning methods with some conditions. The simulator makes it possible to approach empirically to cooperative learning. ’Learning of multi- agent systems’ has not been founded yet as a field of study. Certain points have not been made clear: what is learning of multi-agent systems?; what questions should be raised?; what should be achieved; what should be considered as the cost (for example, should the cost of communication between agents be considered?). We intend to found a field, ’learning of multi-agent systems’, through the experiment of a concrete example of appropriate complicatedness.

/pdf/an-experimental-approach-to-cooperative-learning-of-multi-4acvzxuaeg.pdf

Kazuo Hiraki

Papers

Soccer server: A tool for research on multiagent systems

An experimental approach to cooperative learning of multi-agent systems