[From Rupert Young (2017.09.14 17.00)]
Is anyone particularly familiar with reinforcement learning? What
are its limitations?
From a PCT perspective, what, if any, are its misconceptions, and
what is it lacking?
···
–
Regards,
Rupert
[From Rupert Young (2017.09.14 17.00)]
Is anyone particularly familiar with reinforcement learning? What
are its limitations?
From a PCT perspective, what, if any, are its misconceptions, and
what is it lacking?
–
Regards,
Rupert
From Bruce Abbott (2017.07.14.17235 EDT)]
Rupert Young (2017.09.14 17.00)
RY: Is anyone particularly familiar with reinforcement learning? What are its limitations?
RY: from a PCT perspective, what, if any, are its misconceptions, and what is it lacking?
For info on reinforcement learning as applied in computer science, you might want to check with David Sutton at University College, London. Here’s a link to his introduction to a course on reinforcement learning:
http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching_files/intro_RL.pdf
Bruce
[From Bruce Abbott (2017.09.14.1815 EDT)]
Sorry, senior moment. I meant David Silver. Sutton is a coauthor of one of the leading textbooks on the subject:
Sutton, Richard, & Barto, Andrew N. Reinforcement learning: An introduction.
Bruce
From Bruce Abbott (2017.07.14.17235 EDT)]
Rupert Young (2017.09.14 17.00)
RY: Is anyone particularly familiar with reinforceent learning? What are its limitations?
RY: From a PCT perspective, what, if any, are its misconceptions, and what is it lacking?
For info on reinforcement learning as applied in computer science, you might want to check with David Sutton at University College, London. Here’s a link to his introduction to a course on reinforcement learning:
http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching_files/intro_RL.pdf
Bruce
i had asked about RL and PCT in a previous email, since i am finishing a paper on mice lever pressing – and have had several conversations with bruce since then, so i am happy to talk with you bruce.
Alex Gomez-Marin
behavior-of-organisms.org
I just saw this thread now. I’m decently familiar with RL, if anyone wants another take on it.
Heather
On Fri, Sep 15, 2017 at 8:31 AM, Alex Gomez-Marin agomezmarin@gmail.com wrote:
i had asked about RL and PCT in a previous email, since i am finishing a paper on mice lever pressing – and have had several conversations with bruce since then, so i am happy to talk with you bruce.
On Fri, 15 Sep 2017 at 00:17, Bruce Abbott bbabbott@frontier.com wrote:
[From Bruce Abbott (2017.09.14.1815 EDT)]
Sorry, senior moment. I meant David Silver. Sutton is a coauthor of one of the leading textbooks on the subject:
Sutton, Richard, & Barto, Andrew N. Reinforcement learning: An introduction.
Bruce
From Bruce Abbott (2017.07.14.17235 EDT)]
Rupert Young (2017.09.14 17.00)
RY: Is anyone particularly familiar with reinforceent learning? What are its limitations?
RY: from a PCT perspective, what, if any, are its misconceptions, and what is it lacking?
For info on reinforcement learning as applied in computer science, you might want to check with David Sutton at University College, London. Here’s a link to his introduction to a course on reinforcement learning:
http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching_files/intro_RL.pdf
Bruce
–
Alex Gomez-Marin
behavior-of-organisms.org
–
Heather C. Broccard-Bell, Ph.D.
Postdoctoral Fellow
University of California San Diego
Honey Bee Communication, Nieh Lab
Division of Biological Sciences
Section of Ecology, Behavior, and Evolution
Lecturer
University of San Diego; University of California San Diego
Departments of Psychological Sciences (Psychology); Departments of Biology
619.757.4694
Hey Heather, nice to see you here! Honestly, I don’t think most of them want “another take on it”, as you offer, but only the hard-core-PCT (now Rick-CT) take on it… Don’t waste your time. Hugs, Alex
On Mon, Oct 2, 2017 at 3:37 AM, Heather Bell heather.bell@uleth.ca wrote:
I just saw this thread now. I’m decently familiar with RL, if anyone wants another take on it.
Heather
On Fri, Sep 15, 2017 at 8:31 AM, Alex Gomez-Marin agomezmarin@gmail.com wrote:
i had asked about RL and PCT in a previous email, since i am finishing a paper on mice lever pressing – and have had several conversations with bruce since then, so i am happy to talk with you bruce.
On Fri, 15 Sep 2017 at 00:17, Bruce Abbott bbabbott@frontier.com wrote:
[From Bruce Abbott (2017.09.14.1815 EDT)]
Sorry, senior moment. I meant David Silver. Sutton is a coauthor of one of the leading textbooks on the subject:
Sutton, Richard, & Barto, Andrew N. Reinforcement learning: An introduction.
Bruce
From Bruce Abbott (2017.07.14.17235 EDT)]
Rupert Young (2017.09.14 17.00)
RY: Is anyone particularly familiar with reinforceent learning? What are its limitations?
RY: From a PCT perspective, what, if any, are its misconceptions, and what is it lacking?
For info on reinforcement learning as applied in computer science, you might want to check with David Sutton at University College, London. Here’s a link to his introduction to a course on reinforcement learning:
http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching_files/intro_RL.pdf
Bruce
–
Alex Gomez-Marin
behavior-of-organisms.org
–
Heather C. Broccard-Bell, Ph.D.
Postdoctoral Fellow
University of California San Diego
Honey Bee Communication, Nieh Lab
Division of Biological Sciences
Section of Ecology, Behavior, and Evolution
Lecturer
University of San Diego; University of California San Diego
Departments of Psychological Sciences (Psychology); Departments of Biology
619.757.4694
[From Rupert Young (2017.10.02 13.25)]
Heather, anything you can add to the discussion would be most
welcome (despite any bizarre comments you might get from some
quarters ).
Regards,
Rupert
On 02/10/2017 02:37, Heather Bell
wrote:
I just saw this thread
now. I’m decently familiar with RL, if anyone wants another
take on it.
Heather
On Fri, Sep 15, 2017 at 8:31 AM, Alex
Gomez-Marin agomezmarin@gmail.com
wrote:i had asked about RL and PCT in a
previous email, since i am finishing a paper on mice
lever pressing – and have had several conversations
with bruce since then, so i am happy to talk with you
bruce.
On Fri, 15 Sep 2017 at 00:17, Bruce Abbott
<bbabbott@frontier.com >
wrote:
[From Bruce
Abbott (2017.09.14.1815 EDT)]
Sorry, senior
moment. I meant David Silver. Sutton
is a coauthor of one of the leading
textbooks on the subject:
Sutton,
Richard, & Barto, Andrew N.
Reinforcement learning: An introduction.
Bruce
From Bruce
Abbott (2017.07.14.17235 EDT)]
Rupert Young (2017.09.14 17.00)
RY: Is anyone particularly familiar with
reinforceent learning? What are its
limitations?
RY: From a PCT perspective, what, if any,
are its misconceptions, and what is it
lacking?
For info on reinforcement learning as
applied in computer science, you might
want to check with David Sutton at
University College, London. Here’s a link
to his introduction to a course on
reinforcement learning:
http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching_files/intro_RL.pdf
Bruce
–
Alex Gomez-Marin
[behavior-of-organisms.org](https://urldefense.proofpoint.com/v2/url?u=http-3A__behavior-2Dof-2Dorganisms.org&d=DwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=-dJBNItYEMOLt6aj_KjGi2LMO_Q8QB-ZzxIZIF8DGyQ&m=tURMmMcm1rd_rDdA32ll13z99Kk9FmxF6eIalrBKSKs&s=is_Sc_hcjSOZ0eS-7BNC5WeTXsxy-r2NGWZM0YzBwvA&e=)
Postdoctoral
Fellow
University
of California San Diego
Honey
Bee Communication, Nieh Lab
Division
of Biological Sciences
Section
of Ecology, Behavior, and
Evolution
Lecturer
University
of San Diego; University of
California San Diego
Departments
of Psychological Sciences
(Psychology); Departments of
Biology
619.757.4694