Reinforcement learning and robotic soccer

The presentation (pdf, 932kB, Czech language) for Artificial Intelligence at Charles University in Prague.

Jiří Iša

Teaching
Projects (the newest first)
- Cars in the park 2009 (Outdoor robotic competition)
- Field Robot Event 2009 (Outdoor robotic competition)
- Bee (Robotic vision)
- RobotChallenge 2009 (Puck Collect — Indoor robotic competition)
- Robotour 2008 (Outdoor robotic challenge)
- Winning Reinforcement learning competition 2008 (International competition in reinforcement learning)
- Robotour 2007 (Outdoor robotic delivery challenge)
- Bootloader for ATmega8-board
- Nabamoku (Gomoku playing engine)
- Visiir (Robotic vision - track search)
- Cart-pole system (A well-known reinforcement learning testbed)
- Minirisk (Multi-agent artificial intelligence and/or game theory testbed)
- Hovercraft (Autonomous hovecraft)
- Aygen (The ultimate groan generator)
- Wikipedia 1b (Wikipedia search engine)
- Nyzzuf 1 (Fuzzy neural network)
- FreeBSD ports of Player/Stage/Gazebo (FreeBSD ports of the robotic control and simulation project)
- Trafficsim (Traffic accidents handling, reinforcement learning)
- Lasp I (Statistical language and speech processing)
- CB1D (Real value 1D classification learner)
- Robovis (Visualization of the probabilistic robot localization)
- Graphplan (A classical planning algorithm)
- Robots Ferda and Fatima (Eurobot 2005 international robotic competition)
- Neural Network Motor Controller (Conference article)
- JPresentator (Chess tournaments organization application)
- Pepoun (Lego robot, Kohonen neural network)
- Guido (Unconstrained influence diagrams)
- Botanicus (Distributed genetic algorithm)
- Daama3 (Checkers, advanced alpha-beta algorithm)
- Wumpus (Reinforcement learning)
- Dwarfs (Kohonen neural networks)
- XlsHtmlGUI (Xls to html convertor)
- Maffy (Simulated robosoccer)
- Exprt (Expert system in Prolog)
- Daama (Checkers, advanced alpha-beta algorithm)
- Prsi (Storm) (Card game, neural network)
Presentations
- Unconstrained Influence Diagram Solver: Guido [Outgoing link, new window] (19th IEEE Conference on tools with artificial intelligence - ICTAI 2007)
- Growing Fuzzy Inference Neural Networks (Master thesis topic)
- A polynomial-time Nash equlibrium algorithm for repeated games (based on M. L. Littman & P. Stone article)
- Reinforcement learning dealing with the accidents
  in the traffic control
- Fuzzy decision trees (based on C. Omaru & L. Wehenkel article)
- Scientific visualization (feature extraction and flow field visualization, based on Frits H. Post, Benjamin Vrolijk, Helwig Hauser, Robert S. Laramee and Helmut Doleish article)
- Reinforcement learning and robotic soccer
- Kohonen line following (about Pepoun project, Kohonen neural network, line following)
- Lazy evaluation
  of Bayesian networks
- Reinforcement learning
- Neural networks
Articles
- In the CV
Other
- Sharing a directory on Linux (Sharing a directory on a more advanced filesystems made simple)
- OpenCV troubles (OpenCV problems with Linux&jpeglib&V4L and with FreeBSD)
- RoboTour 2006 (Robotic outdoor challenge)
- Roboludens 2006 (RoboCup European championship)
- Queensday (Queen's day celebration in Amsterdam - photos)
- Keukenhof (Dutch tulip park - photos)
About Jiří Iša (CV)

Last site update: February 25th, 2010