Login / Signup
Contextual Policies Enable Efficient and Interpretable Inverse Reinforcement Learning for Populations.
Ville Tanskanen
Chang Rajani
Perttu Hämäläinen
Christian Guckelsberger
Arto Klami
Published in:
Trans. Mach. Learn. Res. (2024)
Keyphrases
</>
inverse reinforcement learning
reward function
partially observable environments
optimal policy