BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:MARLeME: A Multi-Agent Reinforcement Learning Model Extraction Lib
 rary - Dmitry Kazhdan
DTSTART:20191210T130000Z
DTEND:20191210T140000Z
UID:TALK135751@talks.cam.ac.uk
CONTACT:Mateja Jamnik
DESCRIPTION:Multi-Agent Reinforcement Learning (MARL) encompasses a powerf
 ul class of methodologies that have been applied in a wide range of fields
 . An effective way to further empower these methodologies is to develop li
 braries and tools that could expand their interpretability and explainabil
 ity. In this work\, we introduce MARLeME: a MARL model extraction library\
 , designed to improve explainability of MARL systems by approximating them
  with symbolic models. Symbolic models offer a high degree of interpretabi
 lity\, well-defined properties\, and verifiable behaviour. Consequently\, 
 they can be used to inspect and better understand the underlying MARL syst
 em and corresponding MARL agents\, as well as to replace all/some of the a
 gents that are particularly safety and security critical.
LOCATION:SS03\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR