BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Computer Science - ECPv6.16.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Department of Computer Science
X-ORIGINAL-URL:https://www.cs.jhu.edu
X-WR-CALDESC:Events for Department of Computer Science
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20260308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20261101T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20270314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20271107T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260414T103000
DTEND;TZID=America/New_York:20260414T120000
DTSTAMP:20260517T230225
CREATED:20260317T161135Z
LAST-MODIFIED:20260317T161135Z
UID:1993831-1776162600-1776168000@www.cs.jhu.edu
SUMMARY:CS Seminar Series: Efficient Interactive Learning: Learning More From Less
DESCRIPTION:Refreshments are available starting at 10:30 a.m. The seminar will begin at 10:45 a.m. \nAbstract\nEven as we near the limits of what human-generated data we can scrape from the internet\, today’s decision-making agents—from robots to large language models—are still far from perfect. Thus\, as we start to move past the era of simply scaling up training datasets\, Gokul Swamy believes the most pressing question in decision-making is how we can learn more from less data. \nIn theory\, agents collecting their own data and learning from this experience might allow us to transcend the limits of static datasets. However\, there are two core challenges that make delivering on this promise of reinforcement learning (RL) practically challenging. The first is exploration: experiencing the right things. The second is specification: knowing if what you experienced was good or bad. Swamy’s research focuses on algorithms that address both of these challenges in tandem. \nThis talk will cover both theoretical advancements and their practical implications. First\, Swamy will discuss how we can teach robots to provably recover from their own mistakes without extensive trial-and-error exploration. Second\, he will describe provably robust algorithms for training language models from conflicting preferences. Third\, he will explain how RL learns more from less without having to create data ex nihilo. To conclude\, Swamy will outline what he believes are the most promising directions to enable the next generation of agents to learn even more from less. \nSpeaker Biography\nGokul Swamy is a final-year PhD student in at the Carnegie Mellon University Robotics Institute. He works on efficient interactive learning algorithms for training agents like robots and language models. More fundamentally\, he is interested in techniques for learning to make good decisions efficiently\, even when “good” is hard to specify. Swamy was named a Rising Star in Data Science and Robotics and received an Outstanding Teaching Award for his student mentorship and creation of a new reinforcement learning course. He has also spent summers at Microsoft Research and Google Research. \nZoom link »
URL:https://www.cs.jhu.edu/event/cs-seminar-series-efficient-interactive-learning-learning-more-from-less/
LOCATION:228 Malone Hall
CATEGORIES:Seminars and Lectures
END:VEVENT
END:VCALENDAR