Differences

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

--- start [2025/10/11 06:25]
IIS Webadmin
+++ start [2025/10/23 06:25] (current)
IIS Webadmin
@@ Line 34: / Line 34: @@
 ===== News =====
-<HTML><table><tr valign="top"><td>2025-07-15</td><td>Justus Piater gives an invited keynote <i>Making robots learn to perceive and act with
+<HTML><table><tr valign="top"><td>2025-09-18</td><td>Samuele Tosatto gives an invited keynote <i>Where are all the intelligent robots? A quest for efficiency in reinforcement learning</i> at <a href="https://sarl-plus.github.io/RL-Bootcamp2025/">Reinforcement Learning Bootcamp 2025</a>, Salzburg. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem0', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem0Abstract" style="display:none">As artificial intelligence reshapes our digital world at a breathtaking pace,
+    a curious question arises: Where are all the real-world, intelligent robots?
+    While we have mastered the generation of text, images, and video by leveraging vast web-scale datasets,
+    robotics still faces a fundamental data bottleneck. Reinforcement learning (RL) offers a compelling solution,
+    enabling agents to learn autonomously by collecting their own experience.
+    However, the path to autonomy is often blocked by the staggering inefficiency of current RL algorithms,
+    which can require millions of trials to master simple tasks. This talk embarks on a quest to tackle this
+    efficiency problem head-on. I will argue that a crucial step toward unlocking the potential of
+    robot learning lies in a two-pronged approach: first, by developing statistically efficient
+    algorithms that can reuse data by leveraging sound off-policy techniques, and second,
+    by designing better action representations for physical, real-world agents.
+    By making our algorithms more efficient and refining their core hypotheses,
+    we can accelerate the journey toward real embodied artificial intelligence.</blockquote></td></tr><tr valign="top"><td>2025-07-15</td><td>Justus Piater gives an invited keynote <i>Making robots learn to perceive and act with
     understanding</i> at <a href="https://www.uibk.ac.at/en/congress/multibody2025/">The
-th ECCOMAS Thematic Conference on Multibody Dynamics</a>, Innsbruck. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem0', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem0Abstract" style="display:none">The flexibility and robustness of current robots is
+th ECCOMAS Thematic Conference on Multibody Dynamics</a>, Innsbruck. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem1', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem1Abstract" style="display:none">The flexibility and robustness of current robots is
     limited by their lack of understanding of their environment. For
     this reason, most robots operate in controlled environments.
@@ Line 56: / Line 68: @@
     Rules</a>, Universität Innsbruck.</td></tr><tr valign="top"><td>2025-03-06</td><td>Justus Piater teaches a tutorial <i>Funktionsweise, Möglichkeiten und Grenzen von KI</i> at <a href="https://www.tirol.gv.at/fileadmin/themen/bildung/medienzentrum/downloads/07_Magazin_Co/2025_01.pdf">Lieber
     gleich berechtigt als später: Hallo KI, hilfst du uns bei der
-    Gleichstellung?!</a>, Tiroler Bildungsinstitut Grillhof Vill. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem6', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem6Abstract" style="display:none">Künstliche Intelligenz&quot; bezeichnet derzeit Systeme, die
+    Gleichstellung?!</a>, Tiroler Bildungsinstitut Grillhof Vill. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem7', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem7Abstract" style="display:none">Künstliche Intelligenz&quot; bezeichnet derzeit Systeme, die
     auf maschinellem Lernen (ML) basieren. Dieser Workshop führt in
     die Grundlagen des ML ein, mit besonderem Augenmerk auf neuronale
@@ Line 63: / Line 75: @@
     und Grenzen von ML und warum es mit derzeitigen Mitteln extrem
     schwierig ist, Diskriminierung in KI-Systemen zu
-    verhindern.</blockquote></td></tr><tr valign="top"><td>2025-02-26</td><td>Simon Haller-Seeber and Christopher Kelter teach a tutorial <i>Programmieren eines autonomen Roboters anhand einer selbstentwickelten KI</i> at STAIR-Lab INNALP Workshop für das Gymnasium Ursulinenen Innsbruck, Universität Innsbruck.</td></tr><tr valign="top"><td>2025-02-26</td><td>Marko Zarić teaches a tutorial <i>Einführung in das Programmieren mit Microcontrollern</i> at STAIR-Lab INNALP Workshop für das Gymnasium Ursulinenen Innsbruck, Universität Innsbruck.</td></tr><tr valign="top"><td>2025-01-31</td><td>Justus Piater gives an invited lecture <i>High-Level AI For Autonomous Robots</i> at <a href="https://elias-ai.eu/event/ellis-vismac/">ELIAS-ELLIS-VISMAC
+    verhindern.</blockquote></td></tr><tr valign="top"><td>2025-02-26</td><td>Simon Haller-Seeber and Christopher Kelter teach a tutorial <i>Programmieren eines autonomen Roboters anhand einer selbstentwickelten KI</i> at STAIR-Lab INNALP Workshop für das Gymnasium Ursulinenen Innsbruck, Universität Innsbruck.</td></tr><tr valign="top"><td>2025-02-26</td><td>Marko Zarić teaches a tutorial <i>Einführung in das Programmieren mit Microcontrollern</i> at STAIR-Lab INNALP Workshop für das Gymnasium Ursulinenen Innsbruck, Universität Innsbruck.</td></tr></table></HTML>
-    Winter School 2025</a>, Brunico, Italy. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem9', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem9Abstract" style="display:none">What barriers will have to be overcome to raise the
-    flexibility and robustness of autonomous robots to the next level?
-    I argue that current AI methods are unlikely to get there, no
-    matter how far we scale them up. Robots need to be able to
-    &quot;understand&quot; their environment in ways that reach beyond
-    prediction and control. I will discuss examples of work (ours and
-    others') on learning visual relational concepts, extrapolation of
-    learned movements beyond the training distribution, learning of
-    symbolic concepts and rules, and structure-driven skill learning
-    from sensorimotor experience.</blockquote></td></tr></table></HTML>
 [[news|Older News]]

User Tools

Site Tools

Differences

Page Tools