BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:AMLD 2021 Workshop – Flatland: Multi-Agent Reinforcement Learnin
 g for Trains
DTSTART:20210929T090000
DTEND:20210929T170000
DTSTAMP:20260410T221135Z
UID:404fa05f80715cd60a4bca77061b96f8bc86af586f757a73754325d2
CATEGORIES:Conferences - Seminars
DESCRIPTION:⚠️ A valid COVID certificate must be presented on site t
 o enter the event. ⚠️\n\nThis workshop is a great introduction to the
  Enabling cooperation between multiple agents: information sharing in Mul
 ti-Agent Reinforcement Learning workshop.\n\nScheduling trains is hard: r
 ailway networks are growing fast\, and the decision-making methods commonl
 y used don't scale well. How can we solve this problem? With machine learn
 ing\, of course! In this workshop\, we will use reinforcement learning to 
 tackle this real-world challenge.\nIn the morning\, we will introduce the 
 main reinforcement learning methods. Participants will get familiar with t
 hem by solving toy problems. In the afternoon\, participants will design t
 heir own agents\, which will then compete with other people’s agents in 
 a (friendly) competitive setting.\n\nWe will use the Flatland railway simu
 lator\, developed in collaboration with SBB and Deutsche Bahn. We plan to 
 invite SBB researchers to give insights on this problem\, as well as compe
 titive participants from previous Flatland challenges. Following this work
 shop\, participants can take part in the other full-day Flatland workshop 
 organized by Deutsche Bahn and InstaDeep\, which will introduce the bleedi
 ng-edge innovations they have been working on to tackle this problem.
LOCATION:STCC
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR