UT Computer Science Ranked No. 9 Nationally, Top 10 in AI and Theory in U.S. News & World Report Rankings ...

Transfer Learning for Reinforcement Learning Domains: A Survey. Matthew E. Taylor and Peter Stone. Journal of Machine Learning Research, 10(1):1633–1685, 2009.

Artificial Intelligence and Life in 2030. Peter Stone, Rodney Brooks, Erik Brynjolfsson, Ryan Calo, Oren Etzioni, Greg Hager, Julia Hirschberg, Shivaram ...

Lectures from Spring 2025 January 14, 2025: Trees; Symbol and Binding; let REPL; Clojure Examples let, cons, Structure Sharing first, rest January 16, 2025: Quotation; cons Rules for cons, first, rest ...

to practice using Java ArrayLists to implement a program that uses multiple classes. (object based programming, encapsulation) to practice implementing individual classes based on a given ...

A critical bottleneck limiting imitation learning in robotics is the lack ofdata. This problem is more severe in mobile manipulation, where collectingdemonstrations is harder than in stationary ...

Deep Recurrent Q-Learning for Partially Observable MDPs Deep Recurrent Q-Learning for Partially Observable MDPs. Matthew Hausknecht and Peter Stone. In AAAI Fall Symposium on Sequential Decision ...

Haresh Karnan, Anirudh Nair, Xuesu Xiao, Garrett Warnell, Soren Pirk, Alexander Toshev, Justin Hart, Joydeep Biswas, and Peter Stone. Socially CompliAnt Navigation Dataset (SCAND): A Large-Scale ...

All speakers of the lecture series have received very strict instructions as how to arrange their speech; as a result I expect all speeches to be similar to each other. Mine will not differ, I adhere ...

[edit]F Fabian (born 1943), American former teen idol Fabio (born 1959), Italian fashion model Falco (1957-1998), Austrian musician Fergie (born 1975), American singer-songwriter Fernandel (1903-1971) ...

This note is devoted to three rules, the following of which is necessary if you want to be successful in scientific research. (If you manage to follow them, they will prove close to sufficient, but ...