Assignments |
Notes
Instructor: James R. Glenn, Ph.D.
Office: AKW 013
Office Phone: TBD
Office Hours: Tue 4:00-5:30pm, Wed 12:30-2pm, and by appointment
e-mail: [first name][dot][last name]@yale.edu
Class Meeting:
Lecture Tue, Thu 11:35am – 12:50pm in WLH 015 (online for 1st two weeks; see Canvas for link or e-mail instructor)
Prerequisites: CPSC 474 or CPSC 574
Readings:
Readings vary from semester to semester according to the interests of
the instructor and students. Selected readings from past iterations of
the course include
- F. Lantz, A. Isaksen, A. Jaffe, A. Nealen, J. Togelius, Depth in Strategic Games, Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI 2017), pp. 967-974.
-
Browne, Cameron, Automatic generation and evaluation of recombination games. PhD thesis, Queensland University of Technology, 2008.
-
Nenad TomaĊĦev, Ulrich Paquet, Demis Hassabis, Vladimir Kramnik, Assessing Game Balance with AlphaZero: Exploring Alternative Rule Sets in Chess
-
F. de Mesentier Silva, S. Lee, J. Togelius, A. Nealen, AI-based Playtesting of Contemporary Board Games, Proceedings of the International Conference on the Foundations of Digital Games 2017, pp. 13:1-13:10
-
F. de Mesentier Silva, S. Lee, J. Togelius, A. Nealen, Evolving Maps and Decks for Ticket to Ride, Procedural Content Generation Workshop 2018 Evolving maps and decks for ticket to ride. Proceedings of the 13th International Conference on the Foundations of Digital Games.
-
O. David et al, Genetic Algorithms for Evolving Computer Chess Programs, IEEE Trans. on Evolutionary Computation, 18(5):778-789, 2014
-
Eli David, Nathan S. Netanyahu, Lior Wolf, DeepChess: End-to-End Deep Neural Network for Automatic Learning in Chess, International Conference on Artificial Neural Networks (ICANN), Springer LNCS, Vol. 9887, pp. 88-96, Barcelona, Spain, 2016
-
Ming-Yu Liu, Thomas Breuel, Jan Kautz, Unsupervised Image-to-Image Translation Networks, 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA.
-
D. Sobol, L. Wolf, Y. Taigman, Visual Analogies between Atari Games for Studying Transfer Learning in RL.
-
Shani Gamrian, Yoav Goldberg, Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation, Proceedings of the 36th International Conference on Machine Learning, PMLR 97:2063-2072, 2019.
-
J. Zhu, T. Park, P. Isola and A. A. Efros, Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks, 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017, pp. 2242-2251, doi: 10.1109/ICCV.2017.244 extended version
-
Jason Brownlee, CycleGAN tutorial
-
D. Koller, N. Megiddo, B. von Stengel, Fast Algorithms for Finding Randomized Strategies in Game Trees, Proc. of 26th ACM Symposium on Theory of Computation (STOC), 1994
-
T. Neller and M. Lanctot, An Introduction to Counterfactual Regret Minimization
Catalog Description:
A seminar on current topics in computational intelligence for games,
including developing agents for playing games, procedural content
generation, and player modeling. Students read, present, and discuss
recent papers and competitions, and complete a term-long project that
applies some of the techniques discussed during the term to a game of
their choice.
Course Outcomes:
Students will be able to
- understand and implement current research in computational
intelligence for games
Assignments and Grading:
Students are expected to find research papers and tools relevant to a
project they work on throughout the semester. Students will make
presentations to the class explaining the findings of the papers and
giving tutorials for the tools. Students are expected to participate
in in-class and/or online discussions of other students' presentations.
Grading is based on presentations, discussions, and the
final project and presentation.
Schedule (subject to change):
Week of |
Topics |
Reading |
Events |
Mon |
Tue |
Wed |
Thu |
Fri |