This is really cool work, congrats! Should be useful for generalization in certain types of reinforcement learning tasks too I think.
-
-
-
Yes, indeed that was the original motivation. We have a few threads in those directions, but combining causal discovery with interaction is wide open :)
End of conversation
New 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.