Speaker: Peter Stone, UT Austin

Host: Lydia

Title: Efficient Robot Skill Learning: Grounded Simulation Learning and Imitation Learning from Observation

Abstract:  For autonomous robots to operate in the open, dynamically changing world, they will need to be able to learn a robust set of skills from relatively little experience. This talk begins by introducing Grounded Simulation Learning as a way to bridge the so-called reality gap between simulators and the real world in order to enable transfer learning from simulation to a real robot. It then introduces two new algorithms for imitation learning from observation that enable a robot to mimic demonstrated skills from state-only trajectories, without any knowledge of the actions selected by the demonstrator.

Grounded Simulation Learning has led to the fastest known stable walk on a widely used humanoid robot, and imitation learning from observation opens the possibility of robots learning from the vast trove of videos available online.

Bio: Dr. Peter Stone is the David Bruton, Jr. Centennial Professor and Associate Chair of Computer Science, as well as Chair of the Robotics Consortium, at the University of Texas at Austin. In 2013 he was awarded the University of Texas System Regents’ Outstanding Teaching Award and in 2014 he was inducted into the UT Austin Academy of Distinguished Teachers, earning him the title of University Distinguished Teaching Professor. Professor Stone’s research interests in Artificial Intelligence include machine learning (especially reinforcement learning), multiagent systems, and robotics. Professor Stone received his Ph.D in Computer Science in 1998 from Carnegie Mellon University. From 1999 to 2002 he was a Senior Technical Staff Member in the Artificial Intelligence Principles Research Department at AT&T Labs – Research. He is an Alfred P. Sloan Research Fellow, Guggenheim Fellow, AAAI Fellow, IEEE Fellow, AAAS Fellow, Fulbright Scholar, and 2004 ONR Young Investigator. In 2007 he received the prestigious IJCAI Computers and Thought Award, given biannually to the top AI researcher under the age of 35, and in 2016 he was awarded the ACM/SIGAI Autonomous Agents Research Award. Professor Stone co-founded Cogitai, Inc., a startup company focused on continual learning, in 2015, and currently serves as Executive Director of Sony AI America. 

Speaker: Michael Mitzenmacher, Harvard

Host: Anshu

Title: Algorithms with Predictions : How ML Can Lead to Provably Better Algorithms

Abstract: We survey the recent and growing area of algorithms that use predictions from machine learning applied to the input to circumvent worst-case analysis. We aim for algorithms that have near-optimal performance when these predictions are good, but recover the prediction-less worst case behavior when the predictions have large errors. We focus on work by the speaker on prediction-based scheduling and learned Bloom filters

Bio: Michael Mitzenmacher is a Professor of Computer Science in the School of Engineering and Applied Sciences at Harvard University. Michael has authored or co-authored over 150 conference and journal publications on a variety of topics, including algorithms for the Internet, efficient hash-based data structures, erasure and error-correcting codes, power laws, and compression. His work on low-density parity-check codes shared the 2002 IEEE Information Theory Society Best Paper Award and won the 2009 ACM SIGCOMM Test of Time Award. His textbook on randomized algorithms and probabilistic techniques in computer science was published in 2005 by Cambridge University Press.

Michael Mitzenmacher graduated summa cum laude with a B.A. in mathematics and computer science from Harvard in 1991. After studying mathematics for a year in Cambridge, England, on the Churchill Scholarship, he obtained his Ph. D. in computer science at U.C. Berkeley in 1996. He then worked at Digital Systems Research Center until joining the Harvard faculty in 1999.

Speaker: Lise Getoor, UCI

Host: Lydia

CANCELLED DUE TO COVID