<!DOCTYPE html>
<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
</head>
<body>
<p>reminder: Please come and see Arundhati's thesis defense
happening now<br>
</p>
<div class="moz-forward-container"><br>
<br>
-------- Forwarded Message --------
<table cellpadding="0" cellspacing="0" border="0"
class="moz-email-headers-table">
<tbody>
<tr>
<th valign="BASELINE" align="RIGHT" nowrap="nowrap">Subject:
</th>
<td>Reminder - Thesis Defense - January 17, 2025 - Arundhati
Banerjee - Learning based approaches to practical
challenges in multi-agent active search</td>
</tr>
<tr>
<th valign="BASELINE" align="RIGHT" nowrap="nowrap">Date: </th>
<td>Fri, 17 Jan 2025 12:23:22 -0500</td>
</tr>
<tr>
<th valign="BASELINE" align="RIGHT" nowrap="nowrap">From: </th>
<td>Diane L Stidle <a class="moz-txt-link-rfc2396E" href="mailto:stidle@andrew.cmu.edu"><stidle@andrew.cmu.edu></a></td>
</tr>
<tr>
<th valign="BASELINE" align="RIGHT" nowrap="nowrap">To: </th>
<td><a class="moz-txt-link-abbreviated" href="mailto:ml-seminar@cs.cmu.edu">ml-seminar@cs.cmu.edu</a> <a class="moz-txt-link-rfc2396E" href="mailto:ML-SEMINAR@CS.CMU.EDU"><ML-SEMINAR@CS.CMU.EDU></a>,
<a class="moz-txt-link-abbreviated" href="mailto:yyue@caltech.edu">yyue@caltech.edu</a></td>
</tr>
</tbody>
</table>
<br>
<br>
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
<p><b><i>Thesis Defense</i></b></p>
<p>Date: January 17, 2025<br>
Time: 1:00pm (EST)<br>
Place: GHC 4405 & Remote<br>
PhD Candidate: Arundhati Banerjee</p>
<p><b>Title: Learning based approaches to practical challenges in
multi-agent active search</b></p>
<div>Abstract:<br>
<div>Interactive decision making is essential for the
functioning of autonomous agents in both software and embodied
applications. Typically, agents interact in a multi-agent
environment with the goal of fulfilling individual or shared
objectives. In this thesis, we study the multi-agent adaptive
decision making problem in the framework of Multi-Agent Active
Search (MAAS) with a focus on applications like search and
rescue, wildlife patrolling or environment monitoring with
multi-robot teams. <br>
<br>
Multi-Agent active search involves a team of robots (agents)
deciding <i>when </i>and <i>where</i> to gather information
about their surroundings, conditioned on their past
observations, in order to estimate the presence and position
of different objects of interest (OOIs) or targets. Agents
communicate with each other asynchronously, without relying on
a central controller to coordinate the agents'
interactions. Realistically, inter-agent communications may be
unreliable, and robots in the wild have to deal with noisy
observations and stochastic environment dynamics. Our setup
formalizes MAAS with practical models of real-world sensing,
noise, and communication constraints for aerial and ground
robots. </div>
<div><br>
</div>
<div>Part I of this thesis studies the benefits of non-myopic
lookahead decision making in MAAS with Thompson sampling and
Monte Carlo Tree Search. Additionally, we consider a
multi-objective pareto-optimization setup for cost-aware
active search, highlighting the challenges due to partial
observability, decentralized multi-agent decision making, and
computational complexity with combinatorial action search
spaces. In Part II, we focus on the practical challenges due
to observation noise and dynamic targets in multi-agent active
search and tracking. Our proposed algorithms using Bayesian
filtering in these settings empirically demonstrate the
importance of uncertainty modeling for inference and decision
making with noisy observations due to sensor errors or
environment non-stationarity. Part III shifts focus to
generative models for decision making, particularly the
applicability of diffusion for lookahead MAAS with observation
noise. In the final part, we discuss the broader applicability
of these methods in the context of multi-agent decision making
in robotics and other applications with similar real world
constraints. </div>
<div><br>
<b>Thesis Committee</b>: <br>
</div>
<div><font color="#000000"><span style="font-family:Helvetica">Jeff
Schneider (Chair)</span><br style="font-family:Helvetica">
<span style="font-family:Helvetica">Geoff Gordon</span><br
style="font-family:Helvetica">
<span style="font-family:Helvetica">Barnabás Póczos</span><br
style="font-family:Helvetica">
<span style="font-family:Helvetica">Yisong Yue (Caltech) </span></font><br>
</div>
<div><font color="#000000"><span
style="font-family:Helvetica;font-size:12px"><br>
</span></font></div>
<div>Link to the draft document:</div>
<div><a
href="https://drive.google.com/drive/folders/1YsZgROFeltk4TUVYo-9ldoSlsEkTjaAB?usp=sharing"
class="moz-txt-link-freetext" moz-do-not-send="true">https://drive.google.com/drive/folders/1YsZgROFeltk4TUVYo-9ldoSlsEkTjaAB?usp=sharing</a><br>
</div>
<div><br>
Zoom meeting link:<br>
</div>
<a
href="https://cmu.zoom.us/j/2231085641?pwd=j7ZOUGOHWPnaCe6c2FuCW3Xb0q8cWb.1&omn=99132356799"
moz-do-not-send="true">https://cmu.zoom.us/j/2231085641?pwd=j7ZOUGOHWPnaCe6c2FuCW3Xb0q8cWb.1&omn=99132356799</a><br>
</div>
</div>
</body>
</html>