This work studies the control of robots in the adversarial world of "Hunt the Wumpus". The hybrid learning algorithm which controls the robots behavior is a combination ...
This work presents a lookahead-based exploration strategy for a model-based learning agent that enables exploration of the opponent's behavior during interaction in a multi-a...
In a competitive game it is important to identify the opponent’s strategy as quickly and accurately as possible so that an effective response can be staged. In this vain, this p...
Many learning tasks in adversarial domains tend to be highly dependent on the opponent. Predefined strategies optimized for play against a specific opponent are not likely to succ...
Achim Rettinger, Martin Zinkevich, Michael H. Bowl...
Agents in a competitive interaction can greatly benefit from adapting to a particular adversary, rather than using the same general strategy against all opponents. One method of s...