A long-lived agent continually faces new tasks in its environment. Such an agent may be able to use knowledge learned in solving earlier tasks to produce candidate policies for it...
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...
: ConnectIT uses a graphical representation to express strategies for playing the connect-four game. With this tool we can transfer complex knowledge about the connect-four game it...
Abstract— We consider the problem of apprenticeship learning when the expert’s demonstration covers only a small part of a large state space. Inverse Reinforcement Learning (IR...
Multi-category classification of short dialogues is a common task performed by humans. When assigning a question to an expert, a customer service operator tries to classify the cu...