Intelligent and Interactive Systems

User Tools

Site Tools


news

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
news [2019/12/04 06:25]
IIS Webadmin
news [2019/12/10 06:25] (current)
IIS Webadmin
Line 4: Line 4:
  
 <​HTML><​table><​tr valign="​top"><​td>​2019-10-10</​td><​td>​IIS guest <span style="​font-weight:​bold">​Georg Martius</​span>,​ Max Planck Institute for Intelligent Systems, <​HTML><​table><​tr valign="​top"><​td>​2019-10-10</​td><​td>​IIS guest <span style="​font-weight:​bold">​Georg Martius</​span>,​ Max Planck Institute for Intelligent Systems,
 +    Tübingen, ​ gives an invited colloquium <​i>​Control What You Can – Intrinsically Motivated
 +    Hierarchical RL</​i>​ at IIS Colloquium. <span class="​actions"><​a href="​javascript:​void(0)"​ onclick="​showHide('​newsitem12',​ '​Abstract'​)">​[Abstract]</​a></​span><​blockquote id="​newsitem12Abstract"​ style="​display:​none">​I will present present a hierarchical reinforcement
 +    learning agent that is intrinsically motivated to learn how to
 +    control its observation space in the fastest possible manner by
 +    optimizing learning progress. The agent mimicks to some extend the
 +    development process how a baby learns. ​ Our agent learns what can
 +    be controlled, how to allocate time and attention, and the
 +    relations between objects in the environment. ​ In a nutshell, our
 +    work combines several task-level planning ideas (e.g.,
 +    backtracking search on task graph, probabilistic road-maps,
 +    allocation of search efforts, etc.), in the form of structured
 +    prior, with deep RL control and relational reasoning to learn from
 +    scratch.</​blockquote></​td></​tr><​tr valign="​top"><​td>​2019-10-10</​td><​td>​IIS guest <span style="​font-weight:​bold">​Georg Martius</​span>,​ Max Planck Institute for Intelligent Systems,
     Tübingen, ​ gives an invited colloquium <​i>​Self-Organization of Behavior in Autonomous Robot     Tübingen, ​ gives an invited colloquium <​i>​Self-Organization of Behavior in Autonomous Robot
-    Development</​i>​ at <a href="​https://​www.uibk.ac.at/​informatik/​forschung/​lunchtime-seminar/​index.html.en">​IFI Lunchtime Seminar</​a>​.</​td></​tr><​tr valign="​top"><​td>​2019-07-17</​td><​td>​Matteo Saveriano contributes a talk <​i>​From Intuitive Skill Transfer to Large-Scale Robotic Knowledge Bases</​i>​ at <a href="​https://​www.uibk.ac.at/​disc/​events/">​DiSCourse - The Digital Science Seminar Series</​a>,​ Department of Computer Science, University of Innsbruck.</​td></​tr><​tr valign="​top"><​td>​2019-07-15</​td><​td>​David Peer contributes a talk <​i>​Vector Routing in Capsule Networks</​i>​ at School of Learning, Perception and Robotics (SPROuT), Department of Information Engineering and Computer Science, University of Trento.</​td></​tr><​tr valign="​top"><​td>​2019-07-15</​td><​td>​Sayantan Auddy contributes a talk <​i>​Progress,​ Compress and Expand - A framework for lifelong learning of+    Development</​i>​ at <a href="​https://​www.uibk.ac.at/​informatik/​forschung/​lunchtime-seminar/​index.html.en">​IFI Lunchtime Seminar</​a>​. ​<span class="​actions"><​a href="​javascript:​void(0)"​ onclick="​showHide('​newsitem13',​ '​Abstract'​)">​[Abstract]</​a></​span><​blockquote id="​newsitem13Abstract"​ style="​display:​none">​I am studying the question how robots can autonomously 
 +    develop skills. ​ Considering children, it seems natural that they 
 +    have their own agenda. They explore their environment in a playful 
 +    way, without the necessity for somebody to tell them what to do 
 +    next. With robots the situation is different. There are many 
 +    methods to let robots learn to do something, but it is always 
 +    about learning to do a specific task from a supervision 
 +    signal. Unfortunately,​ these methods do not scale well to systems 
 +    with many degrees of freedom, except a good prestructuring is 
 +    available. ​ The hypothesis is that if the robots first learn to 
 +    use their bodies and interact with the environment in a playful 
 +    way they can acquire many small skills with which they can later 
 +    solve complicated tasks much quicker. In the talk I will present 
 +    my steps into this direction. Starting from some general 
 +    information theoretic consideration we provide robots with an own 
 +    drive to do something and explore their behavioral 
 +    capabilities. Technically,​ this is achieved by considering the 
 +    sensorimotor loop as a dynamical system, whose parameters are 
 +    adapted online according to a gradient ascent on an approximated 
 +    information quantity. ​ I'll show examples of simulated and real 
 +    robots behaving in a self-determined way and present future 
 +    directions.</​blockquote>​</​td></​tr><​tr valign="​top"><​td>​2019-07-17</​td><​td>​Matteo Saveriano contributes a talk <​i>​From Intuitive Skill Transfer to Large-Scale Robotic Knowledge Bases</​i>​ at <a href="​https://​www.uibk.ac.at/​disc/​events/">​DiSCourse - The Digital Science Seminar Series</​a>,​ Department of Computer Science, University of Innsbruck.</​td></​tr><​tr valign="​top"><​td>​2019-07-15</​td><​td>​David Peer contributes a talk <​i>​Vector Routing in Capsule Networks</​i>​ at School of Learning, Perception and Robotics (SPROuT), Department of Information Engineering and Computer Science, University of Trento.</​td></​tr><​tr valign="​top"><​td>​2019-07-15</​td><​td>​Sayantan Auddy contributes a talk <​i>​Progress,​ Compress and Expand - A framework for lifelong learning of
 robotics tasks</​i>​ at School of Learning, Perception and Robotics (SPROuT), Department of Information Engineering and Computer Science, University of Trento.</​td></​tr><​tr valign="​top"><​td>​2019-07-15</​td><​td>​Justus Piater contributes a talk <​i>​Towards Open-Ended Robot Learning</​i>​ at School of Learning, Perception and Robotics (SPROuT), Department of Information Engineering and Computer Science, University of Trento.</​td></​tr><​tr valign="​top"><​td>​2019-07-15</​td><​td>​Matteo Saveriano contributes a talk <​i>​Learning Structured Robotic Tasks via Human Imitation</​i>​ at School of Learning, Perception and Robotics (SPROuT), Department of Information Engineering and Computer Science, University of Trento.</​td></​tr><​tr valign="​top"><​td>​2019-07-12</​td><​td>​Simon Haller and Nicolas Stolz appear in the media: Sport und Roboter gehen Hand in Hand (in Liechtensteiner Vaterland).</​td></​tr><​tr valign="​top"><​td>​2019-07-04</​td><​td>​Simon Haller teaches a tutorial <​i>​Introduction to Prototyping autonomous Robots using the Robot robotics tasks</​i>​ at School of Learning, Perception and Robotics (SPROuT), Department of Information Engineering and Computer Science, University of Trento.</​td></​tr><​tr valign="​top"><​td>​2019-07-15</​td><​td>​Justus Piater contributes a talk <​i>​Towards Open-Ended Robot Learning</​i>​ at School of Learning, Perception and Robotics (SPROuT), Department of Information Engineering and Computer Science, University of Trento.</​td></​tr><​tr valign="​top"><​td>​2019-07-15</​td><​td>​Matteo Saveriano contributes a talk <​i>​Learning Structured Robotic Tasks via Human Imitation</​i>​ at School of Learning, Perception and Robotics (SPROuT), Department of Information Engineering and Computer Science, University of Trento.</​td></​tr><​tr valign="​top"><​td>​2019-07-12</​td><​td>​Simon Haller and Nicolas Stolz appear in the media: Sport und Roboter gehen Hand in Hand (in Liechtensteiner Vaterland).</​td></​tr><​tr valign="​top"><​td>​2019-07-04</​td><​td>​Simon Haller teaches a tutorial <​i>​Introduction to Prototyping autonomous Robots using the Robot
 Operating System (ROS)</​i>​ at Institut für Informatik, Universität Innsbruck.</​td></​tr><​tr valign="​top"><​td>​2019-06-27</​td><​td>​Justus Piater gives an invited talk <​i>​Selbst lernende Roboter der Zukunft</​i>​ at <a href="​http://​www.gmar.at/​aktuell/">​GMAR Robotics Talks Operating System (ROS)</​i>​ at Institut für Informatik, Universität Innsbruck.</​td></​tr><​tr valign="​top"><​td>​2019-06-27</​td><​td>​Justus Piater gives an invited talk <​i>​Selbst lernende Roboter der Zukunft</​i>​ at <a href="​http://​www.gmar.at/​aktuell/">​GMAR Robotics Talks
news.1575437128.txt.gz · Last modified: 2019/12/04 06:25 by IIS Webadmin