BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Teaching Artificial Agents to Understand Language by Modelling Rew
 ard - Edward Grefenstette\, Facebook AI Research
DTSTART:20190221T110000Z
DTEND:20190221T120000Z
UID:TALK118024@talks.cam.ac.uk
CONTACT:Edoardo Maria Ponti
DESCRIPTION:*Abstract*: Recent progress in Deep Reinforcement Learning has
  shown that agents can be taught complex behaviour and solve difficult tas
 ks\, such as playing video games from pixel observations\, or mastering th
 e game of Go without observing human games\, with relatively little prior 
 information. Building on these successes\, researchers such as Hermann and
  colleagues have sought to apply these methods to teach–in simulation–
 agents to complete a variety of tasks specified by combinatorially rich in
 struction languages. In this talk\, we discuss some of these highlights an
 d some of the limitations which inhibit scalability of such approaches to 
 more complex instruction languages (including natural language). Following
  this\, we introduce a new approach\, inspired by recent work in adversari
 al reward modelling\, which constitutes a first step towards scaling instr
 uction-conditional agent training to “real world” language.\n\n*Bio*: 
 Edward Grefenstette is a Research Scientist at Facebook AI Research\, and 
 Honorary Associate Professor at UCL. Prior to this\, he was a Staff Resear
 ch Scientist at DeepMind. He completed his DPhil (PhD) at the University o
 f Oxford in 2013 under the supervision of Profs Coecke and Pulman\, and Dr
  Sadrzadeh\, working on applying category-theoretic tools–initially deve
 loped to model quantum information flow–to model compositionality of dis
 tributed representations in natural language semantics. His recent researc
 h has covered topics at the intersection of deep learning and machine reas
 oning\, addressing questions such as how neural networks can model or unde
 rstand logic and mathematics\, infer implicit or human-readable programs\,
  or learn to understand instructions from simulation.
LOCATION:Faculty of English\, Room SR24
END:VEVENT
END:VCALENDAR