Real biological operant behavior isn't exactly trial and error learning.
Many factors shape and guide initial responses.
What I've noticed in some descriptions of models is the use of optimization for reinforcement to shape responses. In real organisms behavior may be controlled by short or long term outcomes, and may oscillate between this "optimization" based on schedules. This produces variability in the trials which can adjust behavior. Are we seeing these reinforcement models do this?
I skimmed through the book, and it's lacking the information theory foundations. For example, "trust region methods" come from maximizing the policy's relative entropy (to a reference policy) under a tournament system where high-scoring agents are exponentially likely to survive. In general, a reward is the negative bits it costs an environment to propagate an agent (multiplied by some temperature).
I wonder what Sutton thinks about some of the more recent innovations in RL like GRPO. In some ways it’s new, in other ways it’s an echo of RLOO.
Real biological operant behavior isn't exactly trial and error learning.
Many factors shape and guide initial responses.
What I've noticed in some descriptions of models is the use of optimization for reinforcement to shape responses. In real organisms behavior may be controlled by short or long term outcomes, and may oscillate between this "optimization" based on schedules. This produces variability in the trials which can adjust behavior. Are we seeing these reinforcement models do this?
I found this comment/question deeply intriguing.
I’m no expert at this and was wondering what you meant by the following:
> In real organisms behavior may be controlled by short or long term outcomes, and may oscillate between this "optimization" based on schedules
Could you perhaps provide an example that would help me understand what you mean?
Thanks for the insightful comment either way.
I skimmed through the book, and it's lacking the information theory foundations. For example, "trust region methods" come from maximizing the policy's relative entropy (to a reference policy) under a tournament system where high-scoring agents are exponentially likely to survive. In general, a reward is the negative bits it costs an environment to propagate an agent (multiplied by some temperature).
This looks like a good pre-read for Nathan Lambert's https://rlhfbook.com/
Is this riffing on Strunk and Whites: The Elements of Style?
Often referred to as "The Little Book".
Most likely not: “The Little Book of …” has been a publisher’s standby since the nineteenth century (at least).
There are several "Libellus de Miraculis" (Little Book of Miracles) of different saints from the 12th century!
The Little Schemer, The Little Typer, The Little Reasoner, The Little Proover The Little MLer ...
It has been going on for a while in Lispy land
I'm assuming it's more in line with The Little Schemer series of books (https://felleisen.org/matthias/BTLS-index.html) or maybe the little book of deep learning (https://fleuret.org/francois/lbdl.html)?
Proobably the later.
I thought the title was an homage to François Fleuret's Little Book of Deep Learning.
https://fleuret.org/francois/lbdl.html
No, it's _obviously_ homage to the Little Liddel[0].
0. https://archive.org/details/lexiconabridgedf00liddrich
Love that masterpiece
My mind immediately went to the "Li'l Bastard General Mischief Kit" from The Simpsons.
https://imgur.com/zMTEE