Consider the following one-player game. The vertices of a random graph on n vertices are revealed to the player one by one. In each step, also all edges connecting the newly reveal...
Actor-Critic based approaches were among the first to address reinforcement learning in a general setting. Recently, these algorithms have gained renewed interest due to their gen...
: Web-based instruction and online learning are changing customary practices in education. As conventional patterns for content delivery are influenced by new and improving technol...
We study the problem of minimizing the expected loss of a linear predictor while constraining its sparsity, i.e., bounding the number of features used by the predictor. While the r...
The diversity of learning abilities between learners in the virtual classroom is wider than those in traditional classroom. It is difficult to prepare a suitable teaching material ...