BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Multi-Agent Simulation and Learning in TorchRL - Matteo Bettini (U
 niversity of Cambridge)
DTSTART:20231107T130000Z
DTEND:20231107T140000Z
UID:TALK206242@talks.cam.ac.uk
CONTACT:Mateja Jamnik
DESCRIPTION:In this talk\, we will discuss how multi-agent simulation and 
 learning can be performed in the TorchRL library. In particular\, we will 
 focus on showcasing TorchRL's MARL API through a series of examples and de
 mos from the multi-robot systems domain.\nThe talk will begin by introduci
 ng the VectorizedMultiAgentSimulator (VMAS)\, a vectorized simulator compr
 ised of a PyTorch physics engine and a collection of multi-robot tasks. It
  will then focus on discussing how this simulator is integrated in TorchRL
  training library to benefit from on-device  batched simulation and traini
 ng as well as illustrating the general API for integrating any MARL enviro
 nment/game in the library. \nLastly\, it will present an application of th
 e components presented through a live demo of a full multi-agent training 
 pipeline for a multi-robot navigation task.\n\n"You can also join us on Zo
 om":https://cam-ac-uk.zoom.us/j/92041617729
LOCATION:Lecture Theatre 2\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR