<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
</head>
<body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">
<i class="">Department of Computer Science Seminar</i>
<div class=""><b class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;"><br class="">
</b></div>
<div class=""><b class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;">Rika Antonova</b><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;"><br class="">
</span><b class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;">Postdoctoral Scholar</b><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;"><br class="">
</span><b class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;">Stanford University, Interactive Perception and Robot Learning Lab</b><b class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;"><br class="">
</b><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;"><br class="">
</span><b class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;">Thursday, February 16th </b><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;"><br class="">
</span><b class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;">2:00pm - 3:00pm </b><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;"><br class="">
</span><b class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;">In Person: John Crerar Library 390</b><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;"><br class="">
<br class="">
</span><b class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;">Zoom: </b><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;"><br class="">
</span><a href="https://www.google.com/url?q=https://uchicagogroup.zoom.us/j/98654096088?pwd%3DUWsvV0ZhOVp0TytMeFZ4YjBUbkZyZz09&sa=D&source=calendar&ust=1676388857485572&usg=AOvVaw39LlkkE1Yog8952GlqiKRK" target="_blank" class="" style="letter-spacing: 0.20000000298023224px; white-space: pre-wrap;">https://uchicagogroup.zoom.us/j/98654096088?pwd=UWsvV0ZhOVp0TytMeFZ4YjBUbkZyZz09</a><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;"><br class="">
<br class="">
</span><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap; background-color: rgb(255, 255, 255);">Meeting ID: 986 5409 6088</span><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;"><br class="">
</span><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap; background-color: rgb(255, 255, 255);">Passcode: 728867</span><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;"><br class="">
<br class="">
</span><b class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;">Title: Enabling Self-sufficient Robot Learning</b><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;"><br class="">
<br class="">
</span><b class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;">Abstract:</b><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;"><br class="">
</span><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap; background-color: rgb(255, 255, 255);">Autonomous exploration and data-efficient learning are important ingredients for helping machine
learning handle the complexity and variety of real-world interactions. In this talk, I will describe methods that provide these ingredients and serve as building blocks for enabling self-sufficient robot learning.</span><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;"><br class="">
</span><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap; background-color: rgb(255, 255, 255);">First, I will outline a family of methods that facilitate active global exploration. Specifically,
they enable ultra data-efficient Bayesian optimization in reality by leveraging experience from simulation to shape the space of decisions. In robotics, these methods enable success with a budget of only 10-20 real robot trials for a range of tasks: bipedal
and hexapod walking, task-oriented grasping, and nonprehensile manipulation.</span><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;"><br class="">
</span><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap; background-color: rgb(255, 255, 255);">Next, I will describe how to bring simulations closer to reality. This is especially important for
scenarios with highly deformable objects, where simulation parameters influence the dynamics in unintuitive ways. The success here hinges on finding a good representation for the state of deformables. I will describe adaptive distribution embeddings that provide
an effective way to incorporate noisy state observations into modern Bayesian tools for simulation parameter inference. This novel representation ensures success in estimating posterior distributions over simulation parameters, such as elasticity, friction,
and scale, even for scenarios with highly deformable objects and using only a small set of real-world trajectories.</span><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;"><br class="">
</span><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap; background-color: rgb(255, 255, 255);">Lastly, I will share a vision of using distribution embeddings to make the space of stochastic policies
in reinforcement learning suitable for global optimization. This research direction involves formalizing and learning novel distance metrics on this space and will support principled ways of seeking diverse behaviors. This can unlock truly autonomous learning,
where learning agents have incentives to explore, build useful internal representations and discover a variety of effective ways of interacting with the world.</span><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;"><br class="">
<br class="">
</span><b class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;">Bio:</b><span class="" style="caret-color: rgb(60, 64, 67); letter-spacing: 0.20000000298023224px; white-space: pre-wrap;"><br class="">
</span><span class="" style="background-color: rgb(255, 255, 255);">I am a postdoctoral scholar at Stanford University at the Interactive Perception and Robot Learning lab. I received NSF Computing Innovation Fellowship for research on active learning of transferable
priors, kernels, and latent representations for robotics. I completed my Ph.D. work on data-efficient simulation-to-reality transfer at KTH. Earlier, I completed my research Master's degree at the Robotics Institute at Carnegie Mellon University, where I developed
Bayesian optimization approaches for robotics and personalized tutoring systems. Prior to that, I was a software engineer at Google, first in the Search Personalization group and then in the Character Recognition team (developing open-source OCR engine Tesseract).</span></div>
<div class=""><span class="" style="background-color: rgb(255, 255, 255);"><br class="">
</span></div>
<div class=""><img apple-inline="yes" id="46CF1235-165B-4959-86DD-04676CA522C4" class="" src="cid:316FC8A8-4AFA-4423-9077-B4372A1405F5"><span class="" style="background-color: rgb(255, 255, 255);"><br class="">
</span>
<div class="">
<div class=""><br class="">
</div>
<div class="">---</div>
</div>
</div>
<div class="">
<div>Holly Santos<br class="">
Executive Assistant to Michael J. Franklin, Chairman<br class="">
Department of Computer Science<br class="">
The University of Chicago<br class="">
5730 S Ellis Ave-217 Chicago, IL 60637<br class="">
P: 773-834-8977<br class="">
<a href="mailto:hsantos@uchicago.edu" class="">hsantos@uchicago.edu</a><br class="">
</div>
</div>
<br class="">
</body>
</html>