Cooperative Inverse Reinforcement Learning

Abstract

To build systems aligned with human values, machines must act when human objectives are initially unknown. We formalize this cooperative setting as a two-player game with incomplete information: the human knows the reward function, but the robot does not. The robot learns preferences by observing human communicative choices.

Empirical Claims & Epistemic Verification

No formalized claims mapped yet.

Academic Perspectives & Critiques (0)