[FRIAM] Fwd: Talk Announcement: Edward Grefenstette (Facebook AI/UCL) - 8/11 11AM
George Duncan
gtduncan at gmail.com
Tue Aug 18 15:24:10 EDT 2020
---------- Forwarded message ---------
From: Graham Neubig <gneubig at cs.cmu.edu>
Date: Tue, Aug 18, 2020 at 12:02 PM
Subject: Re: Talk Announcement: Edward Grefenstette (Facebook AI/UCL) -
8/11 11AM
To: Graham Neubig <gneubig at cs.cmu.edu>
CC: <ml-phd-students at cs.cmu.edu>, <lti-seminar at cs.cmu.edu>, <
ml-faculty at cs.cmu.edu>
Hi All,
I'd like to share the slides/video for this talk in case you missed it:
Video:
https://drive.google.com/file/d/1UEKG3gEqdxf02kxoVn0Ep4ZTVEyuMd5D/view?usp=sharing
Slides:
https://drive.google.com/file/d/1mByJ_q_5dJALXRQrM8xgX53V6oDq4cxB/view?usp=sharing
Graham
On Wed, Aug 5, 2020 at 8:00 AM Graham Neubig <gneubig at cs.cmu.edu> wrote:
> Hello LTI/ML Students, Faculty,
>
> I'm happy to announce that we'll be holding a virtual talk by Edward
> Grefenstette (https://www.egrefen.com/), a research scientist at Facebook
> AI Research and Honorary Associate Professor at University College London.
> Edward has done some excellent work on machine learning for language
> processing, and in particular he has some nice work at the intersection of
> language and reinforcement learning. Please see the following for more
> details!
>
> -------
>
> Title: Hacking your way to RL in the Real World (someday)
> Time: 8/11 11:00AM
> Link:
> https://cmu.zoom.us/j/92042154213?pwd=aFc2WnMvblZTdUY4WkdSaDFaT0ZOUT09
>
> Deep Reinforcement Learning has produced some impressive results—mostly in
> a particular kind of game or game-like setting—which are worthy of praise.
> However, we (eventually) want agents which do practical stuff in the real
> world. Is the real world like these games? What's the realism gap? Are
> there games that close it a little? All these questions will (possibly) be
> partially and vaguely answered as I present a new environment for RL
> research which will help push the boundaries of our field (without setting
> your cluster on fire), and discuss some recent methods developed to scratch
> the surface of the challenges associated with it.
>
>
>
--
George Duncan
Emeritus Professor of Statistics, Carnegie Mellon University
georgeduncanart.com
See posts on Facebook, Twitter, and Instagram
Land: (505) 983-6895
Mobile: (505) 469-4671
My art theme: Dynamic exposition of the tension between matrix order and
luminous chaos.
"Attempt what is not certain. Certainty may or may not come later. It may
then be a valuable delusion."
>From "Notes to myself on beginning a painting" by Richard Diebenkorn.
"It's that knife-edge of uncertainty where we come alive to our truest
power." Joanna Macy.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://redfish.com/pipermail/friam_redfish.com/attachments/20200818/90226cab/attachment.html>
More information about the Friam
mailing list