Re: Reinforcement Learning (RL) in real time paradigm
Posted: Tue Jan 15, 2019 8:50 pm
Thanks Guenther, that WB forum thread says it pretty well!Guenther wrote: ↑Tue Jan 15, 2019 5:02 pmIt must be over 10 years I have seen Joels name mentioned somewhere, thanks for the paper.Rein Halbersma wrote: ↑Tue Jan 15, 2019 4:52 pm
A similar idea has been proposed before I think: https://papers.nips.cc/paper/3722-boots ... search.pdf
https://www.chessprogramming.org/Bodo
I didn't even know he created 'Meep', because that was shortly before a long hiatus on my side.
https://www.chessprogramming.org/Meep
One of those shorter exchanges between Michael and Bob in the WB forum about Romis learning.
http://www.open-aurec.com/wbforum/viewt ... f=4&t=4835