We propose a new neural network architecture, called Simple Recurrent Temporal-Difference Networks (SR-TDNs), that learns to predict future observations in partially observable en...
Most existing educational games cannot compete with their non-educational counterparts in terms of visual and narrative quality, gameplay, or adaptability. Amongst the most advanc...
Michael D. Kickmeier-Rust, Cord Hockemeyer, Dietri...
This paper presents a novel approach to clustering using an accuracy-based Learning Classifier System. Our approach achieves this by exploiting the generalization mechanisms inher...
Abstract- Seeding the population of an evolutionary algorithm with solutions from previous runs has proved to be useful when learning control strategies for agents operating in a c...
Mitchell A. Potter, R. Paul Wiegand, H. Joseph Blu...
: Student modeling approaches predominantly focus on modeling student knowledge. For effective learning, however, it is necessary to teach students how to learn, as well as to prov...