This webpage gives an overview of my research activities and interests. I have received a PhD doctorate from the Department of Applied Informatics, University of Macedonia, under the supervision of Assistant Professor Ioannis Refanidis. My main research interests are: Artificial Intelligence, Game AI, Machine Learning, Reinforcement Learning, Neural Networks.
You can contact me at nikpapa@gmail.com
The aim of the Palamedes project is to determine if it is possible to create expert game AIs for popular backgammon variants using techniques similar to what is used by strong backgammon programs. The project currently supports the Greek Tavli variants (Portes, Plakoto, Fevga) as well as other popular variants like Narde, Nackgammon, Hypergammon, Takhteh and Tapa. Each game’s expert AI is build using neural networks trained by millions of self-play games using advanced reinforcement learning techniques.
Normally backgammon games are played in a 24-point board using 15 checkers or men per side and 2 six-sided dice. This project attempts to extend the popular backgammon games to arbitrary configurations. Games can be played using different board sizes, number of checkers, and number of die sides. Smaller board configurations make the game easier for players and AI algorithms, while larger board configurations make it more challenging.
| Year | Publication details | Paper |
|---|---|---|
2015 |
Papahristou, N., Decision making in multiplayer environments: Application in backgammon variants. PhD Thesis, University Of Macedonia, Thessaloniki, Greece, 2015 | [download] |
2015 |
Papahristou, N., Refanidis, I., Constructing Pin Endgame Databases for the Backgammon Variant Plakoto., 14th International Conference Advances in Computer Games, ACG 2015, Leiden, The Netherlands, LNCS 9525, pp 177-184, 2015 | [springer] |
2014 |
Papahristou, N., Refanidis, I., Opening Statistics and Match Play for Backgammon Games, Proceedings of 8th Hellenic Conference on Artificial Intelligence, SETN 2014, Ioannina, Greece, LNCS 8445, pp 569-582, 2014 | [springer] |
2013 |
Nikolaos Papahristou and Ioannis Refanidis, AnyGammon: Playing Backgammon Variants Using Any Board Size, Entry at the Research and Experimental Festival of the 8th International Conference on the Foundations of Digital Games, FDG 2013, Chania, Crete, May 2013. | [pdf] |
2012 |
Papahristou, N., Refanidis, I., On the Design and Training of Bots to Play Backgammon Variants, 8th IFIP WG 12.5 Artificial Intelligence Application and Innovations Conference, AIAI 2012, Halkidiki, Greece, September 27-30, 2012, Proceedings, Part I, Volume 381/2012, pp 78-87, 2012 | [springer] |
| Papahristou, N., Refanidis, I., Improving Temporal Difference Performance in Backgammon Variants, 13th Advances in Computer Games Conference, ACG 2011, Tilburg, The Netherlands, November 20-22, 2011, LNCS 7168, pp 134-145, 2012. | [springer] | |
2011 |
Nikolaos Papahristou, Ioannis Refanidis, Training Neural Networks to Play Backgammon Variants Using Reinforcement Learning, Proceedings of Evogames 2011, EvoApplications 2011, Part I, LNCS 6624, pp. 113-122, 2011 | [springer] |
| Year | Award/Honor |
|---|---|
| 2015 | Gold medal at the 2015 Backgammon Computer Olympiad with the Palamedes program. |
| 2012 | Tech Pioneer Award by the PC Magazine Greece. |
| 2011 | Gold medal at the 2011 Backgammon Computer Olympiad with the Palamedes program. |
| 2008 | Greek State Scholarship Foundation (IKY) scholarship awarded (2008). |
© Nikolaos Papahristou, All rights reserved