Preferably a *task* rather than a *technique* (what you are trying to do vs. how you are trying to do it). Too many people jump to tools that may be far from optimal when simpler, better solutions exist
-
-
Show this thread
-
Also, if you are working with a specific dataset, please describe it
Show this thread -
Lots of excellent ideas in this thread! Thanks to everyone who's contributing :)
Show this thread
End of conversation
New conversation -
-
-
I'm looking for practical, non-toy reinforcement learning examples.
-
This! OpenAI Gym problems are not what I'm looking for!
End of conversation
New conversation -
-
-
Reinforcement learning to rank
-
Seconded
- Show replies
New conversation -
-
-
Replace convolution with another kernel!!!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This Tweet is unavailable.
-
Drop "using autoencoders" (one of many possible techniques), keep "comparing/clustering time series".
End of conversation
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.