BEGIN:VCALENDAR
PRODID:-//AddEvent Inc//AddEvent.com v1.7//EN
VERSION:2.0
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:STANDARD
DTSTART:20261101T010000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260308T030000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
DESCRIPTION:Reinforcement learning agents are fundamentally limited by the quality of the reward functions they learn from\, yet reward design is often overlooked under the assumption that a well-defined reward is readily available. However\, in practice\, designing rewards is difficult\, and even when specified\, evaluating their correctness is equally problematic: how do we know if a reward function is correctly specified? In our work\, we address these challenges by focusing on reward alignment -- assessing whether a reward function accurately encodes the preferences of a human stakeholder. As a concrete measure of reward alignment\, we introduce the Trajectory Alignment Coefficient to quantify the similarity between a human stakeholder's ranking of trajectory distributions and those induced by a given reward function. We show that the Trajectory Alignment Coefficient exhibits desirable properties\, such as not requiring access to a ground truth reward\, invariance to potential-based reward shaping\, and applicability to online RL. Additionally\, in an 11 -- person user study of RL practitioners\, we found that access to the Trajectory Alignment Coefficient during reward selection led to statistically significant improvements. Compared to relying only on reward functions\, our metric reduced cognitive workload by 1.5x\, was preferred by 82% of users and increased the success rate of selecting reward functions that produced performant policies by 41%.\n\nCalarina (Callie) Muslimani is a fourth-year PhD student at the University of Alberta in the Reinforcement Learning and Artificial Intelligence (RLAI) Lab\, advised by Matthew E. Taylor. Her research focuses on designing human-aligned reward functions for reinforcement learning\, including developing metrics to evaluate reward functions and creating reward learning algorithms.\n\n------\n\nCreate your own Add to Calendar links with addevent.com/r/a \n
X-ALT-DESC;FMTTYPE=text/html:Reinforcement learning agents are fundamentally limited by the quality of the reward functions they learn from, yet reward design is often overlooked under the assumption that a well-defined reward is readily available. However, in practice, designing rewards is difficult, and even when specified, evaluating their correctness is equally problematic: how do we know if a reward function is correctly specified? In our work, we address these challenges by focusing on reward alignment -- assessing whether a reward function accurately encodes the preferences of a human stakeholder. As a concrete measure of reward alignment, we introduce the Trajectory Alignment Coefficient to quantify the similarity between a human stakeholder's ranking of trajectory distributions and those induced by a given reward function. We show that the Trajectory Alignment Coefficient exhibits desirable properties, such as not requiring access to a ground truth reward, invariance to potential-based reward shaping, and applicability to online RL. Additionally, in an 11 -- person user study of RL practitioners, we found that access to the Trajectory Alignment Coefficient during reward selection led to statistically significant improvements. Compared to relying only on reward functions, our metric reduced cognitive workload by 1.5x, was preferred by 82% of users and increased the success rate of selecting reward functions that produced performant policies by 41%.<br><br>Calarina (Callie) Muslimani is a fourth-year PhD student at the University of Alberta in the Reinforcement Learning and Artificial Intelligence (RLAI) Lab, advised by Matthew E. Taylor. Her research focuses on designing human-aligned reward functions for reinforcement learning, including developing metrics to evaluate reward functions and creating reward learning algorithms.<br /><br />------<br /><br />Create your own Add to Calendar links with addevent.com/r/a <br>
UID:9192d8867ed64d888bd56db4329a300faddeventcom
SUMMARY:Calarina Muslimani - Towards Improving Reward Design in RL: A Reward Alignment Metric for RL Practitioners
DTSTART;TZID=America/Los_Angeles:20251023T090000
DTEND;TZID=America/Los_Angeles:20251023T100000
DTSTAMP:20261004T022225Z
TRANSP:OPAQUE
STATUS:CONFIRMED
SEQUENCE:0
LOCATION:https://meet.google.com/sqj-qimt-yno?hs=122&authuser=0
X-MICROSOFT-CDO-BUSYSTATUS:BUSY
BEGIN:VALARM
TRIGGER:-PT30M
ACTION:DISPLAY
DESCRIPTION:Reminder
END:VALARM
END:VEVENT
END:VCALENDAR