BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2025//talk//TQLGA8
BEGIN:VTIMEZONE
TZID:Europe/Berlin
BEGIN:DAYLIGHT
DTSTART:20240423T000000
TZNAME:CEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20241027T030000
RDATE:20251026T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250330T030000
RDATE:20260329T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Reinforcement Learning Without a PhD: A Python Developer’s Journ
 ey - Jochen Luithardt
DTSTART;TZID=Europe/Berlin:20250423T143000
DTEND;TZID=Europe/Berlin:20250423T150000
DTSTAMP:20261009T075120Z
UID:pretalx-pyconde-pydata-2025-TQLGA8@pretalx.com
DESCRIPTION:Reinforcement Learning (RL) has shown superhuman performance i
 n games and is already delivering value in Big Tech. But despite its poten
 tial\, RL remains largely inaccessible to most developers. Why? Because re
 al-world RL is hard—it demands data\, infrastructure\, and tools that ar
 e often built for researchers\, not practitioners.\n\nThis talk shares the
  journey of applying RL to a real-world use case without having a PhD. It
 ’s a story of figuring things out through hands-on experimentation\, tri
 al and error\, and building what didn’t exist. We’ll explore what make
 s RL powerful\, why it’s still rare in practice\, and how you can get st
 arted. Along the way\, you’ll learn about the key challenges of producti
 on RL\, how to work around them\, and how the open-source toolkit pi_optim
 al can help bridge the gap. Whether you're just RL-curious or ready to div
 e in\, this talk offers practical insights and a demo to help you take you
 r first steps.
LOCATION:Palladium
URL:https://pretalx.com/pyconde-pydata-2025/talk/TQLGA8/
END:VEVENT
END:VCALENDAR