BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Causal Inference and Causal Reinforcement Learning - Chaochao Lu (
 University of Cambridge)
DTSTART:20190227T134500Z
DTEND:20190227T151500Z
UID:TALK120907@talks.cam.ac.uk
CONTACT:Robert Pinsler
DESCRIPTION:We have probably all heard the saying "correlation does not im
 ply causation". But what actually are the differences between a causal and
  a probabilistic model? How can we learn causal relations from data? And w
 hat can causal thinking contribute to machine learning problems such as re
 inforcement learning?\n\nThe first part of this talk (presented by Julius)
  will be a tutorial-style introduction to causal inference from a statisti
 cs and machine learning perspective [1]. After motivating and introducing 
 causal models\, we will present different assumptions for causal inference
  and show how they can all be seen as consequences of a fundamental princi
 ple: the principle of independent mechanisms. We will then present differe
 nt causal discovery methods\, with a focus on learning from observational 
 data alone. Time-permitting\, we will conclude the first part with connect
 ions to semi-supervised and transfer learning.\n\nThe second part of the t
 alk (presented by Chaochao) will focus on Causal Reinforcement Learning (C
 ausal RL)\, which is a promising virgin field and will\, without doubt\, b
 ecome an indispensable part of artificial general intelligence. The philos
 ophy behind the integration of Causal Inference and RL is obvious but char
 ming. That is\, when looking back at the history of science\, human beings
  always progress in a similar manner to that of Causal RL:\n\nHumans summa
 rize rules or experience from their interaction with nature and then explo
 it this to improve their adaptation in the next exploration. What CausalRL
  does is exactly to mimic human behaviors\, learning causal relations from
  an agent communicating with the environment and then optimizing its polic
 y based on the learned causal structures.\n\nIn this talk\, we will learn 
 what Causal RL is\, why we need Causal RL\, and how Causal RL works.
LOCATION:Engineering Department\, CBL Room BE-438
END:VEVENT
END:VCALENDAR