BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T000711Z
LOCATION:704-706
DTSTART;TZID=America/Denver:20231113T153000
DTEND;TZID=America/Denver:20231113T155400
UID:submissions.supercomputing.org_SC23_sess457_ws_mlg103@linklings.com
SUMMARY:Addressing Stale Gradients in Scalable Federated Deep Reinforcemen
 t Learning
DESCRIPTION:Justin Stanley and Ali Jannesari (Iowa State University)\n\nAd
 vancements in reinforcement learning (RL) via deep neural networks have en
 abled their application to a variety of real-world problems. However, thes
 e applications often suffer from long training times. While attempts to di
 stribute training have been successful in controlled scenarios, they face 
 challenges in heterogeneous-capacity, unstable, and privacy critical envir
 onments. This work applies concepts from federated learning (FL) to distri
 buted RL, specifically addressing the stale gradient problem. A determinis
 tic framework for asynchronous federated RL is utilized to explore dynamic
  methods for handling stale gradient updates in the Arcade Learning Enviro
 nment. Experimental results from applying these methods to two Atari-2600 
 games demonstrate a relative speedup of up to 95% compared to plain A3C in
  large and unstable federations.\n\nTag: Artificial Intelligence/Machine L
 earning, Graph Algorithms and Frameworks\n\nRegistration Category: Worksho
 p Reg Pass\n\nSession Chairs: Seung-Hwan Lim (Oak Ridge National Laborator
 y (ORNL)); José Moreira (IBM); Catherine Schuman (University of Tennessee,
  Knoxville); and Richard Vuduc (Georgia Institute of Technology)\n\n
END:VEVENT
END:VCALENDAR