2 citations · 4 across the 5 of their papers we have counts for
5 papers · 1 filter
Contrastive Learning of Preferences with a Contextual InfoNCE Loss
Timo Bertram, Johannes Fürnkranz, Martin Müller
A common problem in contextual preference ranking is that a single preferred action is compared against several choices, thereby blowing up the complexity and skewing the preferenc…
Learning With Generalised Card Representations for "Magic: The Gathering"
Timo Bertram, Johannes Fürnkranz, Martin Müller
A defining feature of collectable card games is the deck building process prior to actual gameplay, in which players form their decks according to some restrictions. Learning to bu…
Efficiently Training Neural Networks for Imperfect Information Games by Sampling Information Sets
Timo Bertram, Johannes Fürnkranz, Martin Müller
In imperfect information games, the evaluation of a game state not only depends on the observable world but also relies on hidden parts of the environment. As accessing the obstruc…
Neural Network-based Information Set Weighting for Playing Reconnaissance Blind Chess
Timo Bertram, Johannes Fürnkranz, Martin Müller
In imperfect information games, the game state is generally not fully observable to players. Therefore, good gameplay requires policies that deal with the different information tha…
Supervised and Reinforcement Learning from Observations in Reconnaissance Blind Chess
Timo Bertram, Johannes Fürnkranz, Martin Müller
In this work, we adapt a training approach inspired by the original AlphaGo system to play the imperfect information game of Reconnaissance Blind Chess. Using only the observations…