TOP
Search the Dagstuhl Website
Looking for information on the websites of the individual seminars? - Then please:
Not found what you are looking for? - Some of our services have separate websites, each with its own search option. Please check the following list:
Schloss Dagstuhl - LZI - Logo
Schloss Dagstuhl Services
Seminars
Within this website:
External resources:
  • DOOR (for registering your stay at Dagstuhl)
  • DOSA (for proposing future Dagstuhl Seminars or Dagstuhl Perspectives Workshops)
Publishing
Within this website:
External resources:
dblp
Within this website:
External resources:
  • the dblp Computer Science Bibliography


Dagstuhl Seminar 11131

Exploration and Curiosity in Robot Learning and Inference

( Mar 27 – Apr 01, 2011 )

(Click in the middle of the image to enlarge)

Permalink
Please use the following short url to reference this page: https://www.dagstuhl.de/11131

Organizers

Contact


Schedule

Summary

This seminar was concerned with answering the question: how should a robot choose its actions and experiences so as to maximise the effectiveness of its learning?.

This seminar was predicated on the assumption that to make significant progress in autonomous robotics, systems level theories of how robots should operate will be required. In recent years methods from machine learning have been employed with great success in robotics, in fields as diverse as visual processing, map building, motor control and manipulation. The machine learning algorithms applied to these problems have included statistical machine learning approaches, such as EM algorithms and density estimation, as well as dimensionality reduction, reinforcement learning, inductive logic programming, and other supervised learning approaches such as locally weighted regression. Most of these robot learning solutions currently require a good deal of supervised learning, or structuring of the learning data for a specific task. As robots become more autonomous these learning algorithms will have to be embedded in algorithms which choose the robot's next learning experience. The problems become particularly challenging in the context of robotics, and even worse for a robot that is faced with many learning opportunities. A robot that can perform both manipulation, language use, visual learning, and mapping may have several quite different learning opportunities facing it at any one time. How should a robot control its curiosity in a principled way in the face of such a variety of choices? How should it choose data on the basis of how much it knows, or on how surprising it finds certain observations? What rational basis should robot designers choose to guide the robot's choice of experiences to learn from? There has been initial progress in several fields, including machine learning, robotics and also in computational neuroscience. In this seminar we brought together these three communities to shed light on the problem of how a robot should select data to learn from, how it should explore its environment, and how it should control curiosity when faced with many learning opportunities.


Participants
  • Peter Auer (Montan-Universität Leoben, AT) [dblp]
  • Andrew Barto (University of Massachusetts - Amherst, US)
  • Anthony Cohn (University of Leeds, GB) [dblp]
  • Peter Dayan (University College London, GB)
  • Richard W. Dearden (University of Birmingham, GB) [dblp]
  • Yiannis Demiris (Imperial College London, GB) [dblp]
  • Stefan Elfwing (Okinawa Institute of Science and Technology, JP)
  • Charles Fox (University of Sheffield, GB)
  • Martin A. Giese (Universitätsklinikum Tübingen, DE)
  • Marc Hanheide (University of Birmingham, GB) [dblp]
  • Mark D. Humphries (ENS - Paris, FR)
  • Kristian Kersting (Fraunhofer IAIS - St. Augustin, DE) [dblp]
  • Andreas Krause (ETH Zürich, CH) [dblp]
  • Ales Leonardis (University of Birmingham, GB) [dblp]
  • Manuel Lopes (INRIA - Bordeaux, FR) [dblp]
  • Ruben Martinez-Cantin (CUD - Zaragoza, ES)
  • Leo Pape (IDSIA - Manno, CH)
  • Jan Peters (TU Darmstadt, DE) [dblp]
  • Daniel Polani (University of Hertfordshire, GB) [dblp]
  • Jürgen Schmidhuber (IDSIA - Manno, CH) [dblp]
  • Frank Sehnke (ZSW- Stuttgart, DE)
  • Danijel Skocaj (University of Ljubljana, SI)
  • Aaron Sloman (University of Birmingham, GB) [dblp]
  • Janusz Starzyk (Ohio University, US)
  • Naftali Tishby (The Hebrew University of Jerusalem, IL) [dblp]
  • John K. Tsotsos (York University - Toronto, CA) [dblp]
  • Eiji Uchibe (Okinawa Institute of Science and Technology, JP)
  • Ales Ude (Jozef Stefan Institute - Ljubljana, SI) [dblp]
  • Patrick van der Smagt (DLR - Oberpfaffenhofen, DE)
  • Markus Vincze (TU Wien, AT) [dblp]
  • Jeremy L. Wyatt (University of Birmingham, GB) [dblp]
  • Jure Zabkar (University of Ljubljana, SI) [dblp]

Classification
  • data structures / algorithms / complexity

Keywords
  • Exploration control
  • dual control
  • optimal control
  • active learning
  • curiosity
  • robot learning
  • exploration