BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Prof. Alexander Mathis's Lab: Alberto Chiappa "Novel methods to ta
 ckle adaptive reinforcement learning"
DTSTART:20220330T160000
DTEND:20220330T164500
DTSTAMP:20260510T043153Z
UID:72419b89170988b3159b835c71176bcc4b45233e92176b134e8a4432
CATEGORIES:Conferences - Seminars
DESCRIPTION:Online by invitation only\n\nThe ability to adapt is a disting
 uishing feature of intelligent systems. In nature\, animals and humans pro
 ve remarkable adaptation skills\, both when changes occur in the external 
 environment and in their body. The sensorimotor system is a particularly r
 elevant example\, as it can often seamlessly recover task performance when
  perturbed. \n \nReinforcement Learning (RL) is the ideal learning frame
 work to experiment with sensorimotor systems\, because it enables the trai
 ning of autonomous agents with complex control skills. While the classical
  formulation of an RL problem considered the same environment for training
  and testing\, in recent years different testing frameworks\, which evalua
 te the performance of an autonomous agent in the presence of perturbations
 \, have emerged\, opening new challenging research directions. I will talk
  about two methods for adaptive reinforcement learning: reinterpreting pas
 t experiences and learning state-dependent controllers.\n 
LOCATION:
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR