An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning

Dhruv Malik, Malayandi Palaniappan, Jaime F. Fisac, Dylan Hadfield-Menell, Stuart J. Russell, Anca D. Dragan

Abstract: Our goal is for AI systems to correctly identify and act according to their human user’s objectives. Cooperative Inverse Reinforcement Learning (CIRL) formalizes this value alignment problem as a t...