Case Studies for Education in Robotics: From Serious Games to "Technology to Teach Technology" Platforms

@inproceedings{Drgoicea2015CaseSF,
  title={Case Studies for Education in Robotics: From Serious Games to "Technology to Teach Technology" Platforms},
  author={Monica Drăgoicea and Theodor Borangiu},
  booktitle={RAAD},
  year={2015}
}
This paper describes a specific perspective on developing case studies related to education in robotics. The proposed framework intends to support students learning how to develop distributed software applications through functionality composition. The multi-agent approach is used as a test bed for case studies development. It tries to stress the role of the application development platform in creating rich simulations, giving students the possibility to express their goals with clarity, and… 
1 Citations
A study of count-based exploration and bonus for reinforcement learning
TLDR
A method of count-based exploration and bonus for reinforcement learning, by introducing the count for state-action visitation into the Boltzmann distribution method as a new behavioral exploration strategy, and adding count- based exploration bonus to guide the agent to exploration.

References

SHOWING 1-10 OF 31 REFERENCES
Robocode: using games to teach artificial intelligence
TLDR
A game called Robocode is described that allows the development of virtual robots using the Java language and is incorporated into an artificial intelligence class and provides students with tools for developing practical versions of the algorithms discussed in class.
PRESAGE: A Programming Environment for the Simulation of Agent Societies
TLDR
A software environment is described which can be used for simulation and animation of agent societies, allowing a system designer to investigate the complex social behaviour of components, the evolution of network structures, and the adaptation of conventional rules.
An Introductory Course on Service-Oriented Computing for High Schools
TLDR
Service-Oriented Computing has been described as a method to build distributed applications more effectively and has the potential to become the first computing course that shifts the course content from the syntax of programming languages to the problem solving process.
Agent-Based Service-Oriented Computing
TLDR
This book is a collection of chapters from experts in the field, that gives an overview of the state-of-the-art in the main areas of current research, and identifies likely future directions.
Evolving Robocode tanks for Evo Robocode
  • R. Harper
  • Computer Science, Biology
    Genetic Programming and Evolvable Machines
  • 2014
TLDR
This system harnessed co-evolution to evolve relatively complex behaviours, within the program size constraints of the competition, and performed as well as those evolved using a hand crafted fitness function, scoring well against such robots in head to head battles.
Modern AI for games : RoboCode
TLDR
Results show that such machine learning methods can create behaviour that is able to satisfactorily compete against other Robocode tanks.
How to Do Agent-Based Simulations in the Future: From Modeling Social Mechanisms to Emergent Phenomena and Interactive Systems Design
TLDR
This work will discuss the techniques of agent-based modeling (ABM) and multi-agent simulation (MAS), including the challenges, perspectives and limitations of the approach.
Distributed Intelligent Systems: A Coordination Perspective
TLDR
The absence of a single unified approach in addressing multi-agent coordination problems arising in any system or organization is identified, highlighting the lack of coherence and order in the area of research pertaining to coordination of distributed intelligent systems.
SOMA-ME: A platform for the model-driven design of SOA solutions
TLDR
Extensibility, traceability, variation-oriented design, and automatic generation of technical documentation and code artifacts are shown to be some of the properties of the SOMA-ME tool.
...
...