BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Reinforcement Learning for Real-World Robotics
DTSTART:20190704T153000
DTEND:20190704T163000
DTSTAMP:20260407T183826Z
UID:c87135ffdc711e7d6a4271e1207407af3287a80b87e450749c72bfd2
CATEGORIES:Conferences - Seminars
DESCRIPTION:Dr. Tuomas Haarnoja (DeepMind)  \nThe intersection of expres
 sive\, general-purpose function approximators\, such as neural networks\, 
 with general-purpose model-free reinforcement learning holds the promise o
 f automating the acquisition of a wide range of robotic skills: reinforcem
 ent learning provides the formalism for reasoning about sequential decisio
 n making\, while large neural networks can provide a general representatio
 n for any behavior. However\, learning behaviors from scratch via deep rei
 nforcement learning in real-world robotic domains has proven to be challen
 ging\, and only recently\, we have started to see progress mainly due to i
 mproved sample complexity and stability of such methods. In this talk\, I 
 will first describe my work at the intersection of robotics and deep reinf
 orcement learning\, focusing on learning robot skills from scratch in the 
 absence of prior knowledge\, and then discuss the biggest limitations and 
 most promising future directions.\n\nDr. Tuomas Haarnoja is a research sci
 entist at Google Deepmind. He did his doctoral thesis with Pieter Abbeel a
 nd Sergey Levine at the Berkeley AI Research Lab (BAIR)\, where he became 
 well known for his work on maximum entropy reinforcement learning\, which 
 provides a theoretically grounded framework for learning stochastic polici
 es that are both sample efficient and reliable\, and its applications to r
 obotic manipulation and locomotion.
LOCATION:SV 1717 https://plan.epfl.ch/?room==SV%201717
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR