In this paper we consider the problem of policy evaluation in reinforcement learning, i.e., learning the value function of a fixed policy, using the least-squares temporal-differe...
Alessandro Lazaric, Mohammad Ghavamzadeh, Ré...
When modeling high-dimensional richly structured data, it is often the case that the distribution defined by the Deep Boltzmann Machine (DBM) has a rough energy landscape with man...
We present the design of Make a Riddle and TeleStory, educational applications developed on the Siftables platform for children aged 4-7 years. Siftables
are
hybrid tangible-g...
: Based on the study of different coordination theories and approaches and on the previous ethnographic case studies, authors identify certain types of coordination, which they int...
Many computational problems in game theory, such as finding Nash equilibria, are algorithmically hard to solve. This limitation forces analysts to limit attention to restricted su...