New Draft of “Reinforcement Learning: An Introduction, Second Edition”

Post by piedradura » Sat, Sep 24, 2016, 10:27 PM UTC

pierrelux wrote: post #29

piedradura wrote: post #19

just reading page 15, arg max = maximal ..., I think that global maximum or local maximum is better than maximal. I would like to read all the interesting fruit of RL in just one hour, can someone suggest a short book for someone with advanced maths skills? Thanks a lot to the authors the book seems to be really interesting. Edit: In page 25, an extended example: tic-tac-toe the rule to update the value of each state…

Short and mathematical: "Algorithms for Reinforcement Learning". PDF available: https://sites.ualberta.ca/~szepesva/RLBook.html

Post by nicklaf » Mon, Sep 26, 2016, 7:36 PM UTC

nicklaf wrote: post #7

I've uploaded a mirror of the PDF: https://instant.io/#678d0be07a0f2260ec6f9b134ec0a1d7c4325e99 If you can, leave the tab open for a while to keep seeding the file! (It's a torrent.)

Post by davidmpaz » Tue, Sep 27, 2016, 6:01 AM UTC

nicklaf wrote: post #34

nicklaf wrote: post #7

I've uploaded a mirror of the PDF: https://instant.io/#678d0be07a0f2260ec6f9b134ec0a1d7c4325e99 If you can, leave the tab open for a while to keep seeding the file! (It's a torrent.)

Looks like the author has a new URL for the PDF, hosted by the university: https://webdocs.cs.ualberta.ca/~sutton/book/bookdraft2016sep... Since it is a draft, the author's new link is the right one to read, since the torrent I posted might be out of date by the time you read this.