The Little Book of Reinforcement Learning
1–10 of 29 posts
Re: The Little Book of Reinforcement Learning
#2Is this riffing on Strunk and Whites: The Elements of Style?
Often referred to as "The Little Book".
Re: The Little Book of Reinforcement Learning
#3Is this riffing on Strunk and Whites: The Elements of Style? Often referred to as "The Little Book".
[dead]
Re: The Little Book of Reinforcement Learning
#4Is 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).
Re: The Little Book of Reinforcement Learning
#5Is this riffing on Strunk and Whites: The Elements of Style? Often referred to as "The Little Book".
Love that masterpiece
Re: The Little Book of Reinforcement Learning
#6This looks like a good pre-read for Nathan Lambert's https://rlhfbook.com/
Re: The Little Book of Reinforcement Learning
#7Is this riffing on Strunk and Whites: The Elements of Style? Often referred to as "The Little Book".
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)?
Re: The Little Book of Reinforcement Learning
#8Is this riffing on Strunk and Whites: The Elements of Style? Often referred to as "The Little Book".
No, it's _obviously_ homage to the Little Liddel[0].
Re: The Little Book of Reinforcement Learning
#9Is this riffing on Strunk and Whites: The Elements of Style? Often referred to as "The Little Book".
My mind immediately went to the "Li'l Bastard General Mischief Kit" from The Simpsons.
Re: The Little Book of Reinforcement Learning
#10Real 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?