BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Inductive Biases for Robot Reinforcement Learning
DTSTART:20230623T110000
DTEND:20230623T120000
DTSTAMP:20260507T203258Z
UID:52c1aa32adf1d54acd42880f963cae278ff3c4abb8d2361d78ea95da
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Jan Peters\, Technische Universitaet Darmstadt\, German
 y\n Abstract\n\nAutonomous robots that can assist humans in situations of
  daily life have been a long standing vision of robotics\, artificial inte
 lligence\, and cognitive sciences. A first step towards this goal is to cr
 eate robots that can learn tasks triggered by environmental context or hig
 her level instruction. However\, learning techniques have yet to live up t
 o this promise as only few methods manage to scale to high-dimensional man
 ipulator or humanoid robots. In this talk\, we investigate a general frame
 work suitable for learning motor skills in robotics which is based on the 
 principles behind many analytical robotics approaches. To accomplish robot
  reinforcement learning learning from just few trials\, the learning syste
 m can no longer explore all learn-able solutions but has to prioritize one
  solution over others – independent of the observed data. Such prioritiz
 ation requires explicit or implicit assumptions\, often called ‘inductio
 n biases’ in machine learning. Extrapolation to new robot learning tasks
  requires induction biases deeply rooted in general principles and domain 
 knowledge from robotics\, physics and control. Empirical evaluations on a 
 several robot systems illustrate the effectiveness and applicability to le
 arning control on an anthropomorphic robot arm. These robot motor skills r
 ange from toy examples (e.g.\, paddling a ball\, ball-in-a-cup) to playing
  robot table tennis\, juggling and manipulation of various objects.\n\n B
 io\n\nJan Peters is a full professor (W3) for Intelligent Autonomous Syste
 ms at the Computer Science Department of the Technische Universitaet Darms
 tadt since 2011\, and\, at the same time\, he is the dept head of the rese
 arch department on Systems AI for Robot Learning (SAIROL) at the German Re
 search Center for Artificial Intelligence (Deutsches Forschungszentrum fü
 r Künstliche Intelligenz\, DFKI) since 2022. He is also is a founding res
 earch faculty member of the Hessian Center for Artificial Intelligence. Ja
 n Peters has received the Dick Volz Best 2007 US PhD Thesis Runner-Up Awar
 d\, the Robotics: Science & Systems - Early Career Spotlight\, the INNS Yo
 ung Investigator Award\, and the IEEE Robotics & Automation Society's Earl
 y Career Award as well as numerous best paper awards. In 2015\, he receive
 d an ERC Starting Grant and in 2019\, he was appointed IEEE Fellow\, in 20
 20 ELLIS fellow and in 2021 AAIA fellow.\nDespite being a faculty member a
 t TU Darmstadt only since 2011\, Jan Peters has already nurtured a series 
 of outstanding young researchers into successful careers. These include ne
 w faculty members at leading universities in the USA\, Japan\, Germany\, F
 inland and Holland\, postdoctoral scholars at top computer science departm
 ents (including MIT\, CMU\, and Berkeley) and young leaders at top AI comp
 anies (including Amazon\, Boston Dynamics\, Google and Facebook/Meta).\nJa
 n Peters has studied Computer Science\, Electrical\, Mechanical and Contro
 l Engineering at TU Munich and FernUni Hagen in Germany\, at the National 
 University of Singapore (NUS) and the University of Southern California (U
 SC). He has received four Master's degrees in these disciplines as well as
  a Computer Science PhD from USC. Jan Peters has performed research in Ger
 many at DLR\, TU Munich and the Max Planck Institute for Biological Cybern
 etics (in addition to the institutions above)\, in Japan at the Advanced T
 elecommunication Research Center (ATR)\, at USC and at both NUS and Siemen
 s Advanced Engineering in Singapore. He has led research groups on Machine
  Learning for Robotics at the Max Planck Institutes for Biological Cyberne
 tics (2007-2010) and Intelligent Systems (2010-2021).\n 
LOCATION:ME C2 405
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR