Abstract: Offline reinforcement learning is important in domains such as medicine, economics, and e-commerce where online experimentation is costly, dangerous or unethical, and where the true model is unknown. However,...
Abstract: Offline reinforcement learning is important in domains such as medicine, economics, and e-commerce where online experimentation is costly, dangerous or unethical, and where the true model is unknown. However,...
This talk is presented in partnership with the Center for Intelligent Information Retrieval (CIIR) as part of its CIIR Talk Series.
Abstract: Being able to answer questions about why people perform particular...
Lunch for attendees (faculty and staff only) will be available by 11:30 a.m. for the noon meeting. For any questions about the food being served, please contact the events team.
To find out more details about the...
Matrices are ubiquitous mathematical structures that arise throughout computer science. We study fast algorithms for several central problems involving matrices, including eigenvalue approximation, spectral approximation...
Microsoft will host a virtual internship info session for both undergrad and grads (masters and Ph.D.) students on September 18th at 5:30 pm. Microsoft is looking for software engineers, data scientists, program/product...
All are encouraged to attend this research presentation led by CICS Assistant Professor Donghyun Kim about the human-centered development of a robotic guide dog. Refreshments will be provided.
The Product Management Club meets weekly on Tuesday nights to discuss trends in technology, conduct product thinking seminars, work on case studies, read books, and occasionally prep together for PM recruitment. All UMass...
For the strongest computer science undergraduates at the University of Massachusetts Amherst and the participating five-colleges, the Manning College of Information and Computer Sciences offers students three special...
Recent advances in mobile computing and the Internet of Things (IoT) enable the global integration of heterogeneous smart devices via wireless networks. A common characteristic across these modern day systems is their...
Abstract: As long as a model appears to describe the relevant aspects of the world satisfactorily, we may continue, cautiously, to use it; when it fails to do so, we need to search for a better one. In particular, any...