[Adapt] Seminar: A Brief Introduction of Reinforcement Learning and RL in text generation

[kelsey]

Hi Adapters,


This time I'm going to talk about Reinforcement Learning with policy gradient. I'll first introduce the overall Neural  Network structure in RL with PG, and then I'll give you a brief introduction about how to apply RL in text generation.


There is an excellent blog about RL with PG written by Karpathy:
http://karpathy.github.io/2016/05/31/rl/


And the paper involved this time is here:
https://arxiv.org/pdf/1511.06732.pdf


Have a nice day! :)


Time: Wed 4:30 pm
Venue: Room 3-517 


See you then,
Kelsey



发自我的iPhone
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20171127/a1ec55f4/attachment.html>