Recently, an Artificial Intelligence software created by Google beat the 3-time European Go champion, Fan Hiu, an achievement believed to be at least 10 years away. Learning how to develop algorithms that can beat the best human players has always been a great challenge and a very active field of research on Artificial Intelligence.
In this seminar, we will present general artificial intelligence techniques for playing games, and use them to program software players for a board game that will be decided on the seminar. All players will compete against each other on weekly tournaments.
Each student will program one or more players, and after each weekly tournament, will receive a detailed log of the matches of his/her player(s). Some specific games might be watched on the seminar, for insights on how each player is performing (and for the fun of it). With the game logs, each student can improve his/her player code to create a more competitive player for the next tournament round.
After some weeks, a final tournament will be played, and then each student will present a detailed talk about the techniques used on his programmed player. Students also have to hand in a 3-6 page summary.
Frequency | Weekday | Time | Format / Place | Period |
---|
Module | Course | Requirements | |
---|---|---|---|
39-Inf-EGMI Ergänzungsmodul Informatik | vertiefendes Seminar 1 | Ungraded examination
|
Student information |
vertiefendes Seminar 2 | Ungraded examination
|
Student information | |
vertiefendes Seminar 3 | Ungraded examination
|
Student information | |
vertiefendes Seminar 4 | Ungraded examination
|
Student information |
The binding module descriptions contain further information, including specifications on the "types of assignments" students need to complete. In cases where a module description mentions more than one kind of assignment, the respective member of the teaching staff will decide which task(s) they assign the students.