Potential-based shaping was designed as a way of introducing background knowledge into model-free reinforcement-learning algorithms. By identifying states that are likely to have ...
We propose an opponent modeling approach for no-limit Texas hold-em poker that starts from a (learned) prior, i.e., general expectations about opponent behavior and learns a relat...
Marc J. V. Ponsen, Jan Ramon, Tom Croonenborghs, K...
We present an approach to building a verb lexicon compatible with WordNet but with explicitly stated syntactic and semantic information, using Levin verb classes to systematically...
We present a highly efficient incremental algorithm for propagating bounded knapsack constraints. Our algorithm is based on the sublinear filtering algorithm for binary knapsack c...
In this work we study the collective behavior in a model of a simplified homogeneous society. Each agent is modeled as a binary “perceptron”, receiving neighbors’ opinions a...