Our #ICLR2019 paper on #activelearning with partial feedback. It is expensive to obtain full information from labeler: e.g. picking fine-grained category. Can the algorithm actively decide what to ask labeler? Can we move on to a different example in a strategic way?https://twitter.com/HuPeiyun/status/1087745819086745600 …
-
-
Actively seeking preferences - in planning http://utdallas.edu/~sriraam.natarajan/Papers/PGPlannerKBSPreprint.pdf …, in probabilistic logic learning http://utdallas.edu/~sriraam.natarajan/Papers/activeadviceseeking.pdf … in IRL http://utdallas.edu/~sriraam.natarajan/Papers/aasirl_AAMAS.pdf …
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Our work on doing this for RL and Relational RL is under preparation. Happy to share a version when ready
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
BTW the entire codebase is available herehttps://starling.utdallas.edu/software/
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.