Using Coordination Graphs to add Prior Knowledge to the RoboCup Domain
نویسندگان
چکیده
Acknowledgements Although the actual writing of this thesis has been done by one person, there are a number of people without whom this thesis had never been written. These people, by offering support, ideas, critiques and various comments related and completely unrelated to the subject of this thesis, have guided the writing of this thesis as much as I did myself. First and foremost, out of a tradition I have found to be completely justified, I would like to thank my supervisors Nikos and Jelle. Both have been invaluable during the course of my research, both providing an endless (and sometimes quite overwhelming) stream of ideas and comments. Without Jelle's expertise of the UvA Trilearn team at least half of my research would have been impossible to do. The other half would not have existed if not for Nikos. Nikos, if I did not often take up your offer of stopping by with questions whenever I wanted, the offer was highly appreciated, and the answers you provided when I did ask were always helpful. A great amount of gratitude goes out to my family, for enduring me during the last year, for helping me get back to the right track after I had taken a wrong turn, but especially, for keeping my spirits up when things were not going as planned. Special thanks go to my mother, who was foremost in keeping me realistic with respect to deadlines (a lesson I will not quickly forget), and who has willingly subjected herself to countless readings and rereadings. Finally there are a number of people who have also contributed, in their own way, to the writing of this thesis and my general well-being during this time. Nina, who did her utmost best to understand what I was doing and succeeded only partly, but was a great support nonetheless. Jan, who didn't decide to become a PhD student at the UvA to keep me company during and after lunches, but who did so anyway, providing me with much-needed breaks and useful commentary in the process. Matthijs, who was a great help in typesetting and formatting my thesis, and who had some valuable comments to add when he was not paying attention.
منابع مشابه
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 کاملMulti-robot decision making using coordination graphs
Within a group of cooperating agents the decision making of an individual agent depends on the actions of the other agents. In dynamic environments, these dependencies will change rapidly as a result of the continuously changing state. Via a context-specific decomposition of the problem into smaller subproblems, coordination graphs offer scalable solutions to the problem of multiagent decision ...
متن کاملAn Unsupervised Learning Method for an Attacker Agent in Robot Soccer Competitions Based on the Kohonen Neural Network
RoboCup competition as a great test-bed, has turned to a worldwide popular domains in recent years. The main object of such competitions is to deal with complex behavior of systems whichconsist of multiple autonomous agents. The rich experience of human soccer player can be used as a valuable reference for a robot soccer player. However, because of the differences between real and simulated soc...
متن کاملDistributed decision making of robotic agents
In order to make a distributed decision in a group of agents, each agent has to take into account the actions of the agents on which it depends. In a dynamic environment, these dependencies may change rapidly as a result of the continuously changing state. Coordination graphs offer a scalable solution to the problem of multiagent coordination by decomposing the problem into smaller subproblems....
متن کاملFrom Sketch To Plan
One of the most important tasks in the RoboCup soccer leagues is to build up soccer domain knowledge for decision-making. Therefore, most RoboCup teams adapt tactics graphs to develop their agents’ behavior manually. This is a very laborious and time-consuming
متن کاملHigh level coordination of agents based on multiagent Markov decision processes with roles
We present an approach for coordinating the actions of a team of real world autonomous agents on a high level. The method extends the framework of multiagent Markov decision processes with the notion of roles, a flexible and natural way to give each member of the team a clear description of its task. A role in our framework defines the set of actions and the policy of an agent. Roles are a natu...
متن کامل