Policy Teaching via Data Poisoning in Learning from Human Preferences.
Andi Nika, Jonathan Nther, Debmalya Mandal, Parameswaran Kamalaruban, Adish Singla, Goran Radanovic
Browse the full AISTATS paper archive.
Andi Nika, Jonathan Nther, Debmalya Mandal, Parameswaran Kamalaruban, Adish Singla, Goran Radanovic
Browse the full AISTATS paper archive.