We consider the problem of incorporating end-user advice into reinforcement learning (RL). In our setting, the learner alternates between practicing, where learning is based on ac...
Kshitij Judah, Saikat Roy, Alan Fern, Thomas G. Di...
In this paper, we show how the dynamics of Q-learning can be visualized and analyzed from a perspective of Evolutionary Dynamics (ED). More specifically, we show how ED can be use...
A mobile agent with the task to classify its sensor pattern has to cope with ambiguous information. Active recognition of three-dimensional objects involves the observer in a sear...
Proactive assessment of computer-network vulnerability to unknown future attacks is an important but unsolved computer security problem where AI techniques have significant impact...
Canonical problems are simplified representations of a class of real world problems. They allow researchers to compare algorithms in a standard setting which captures the most im...