Inferring Reward Functions from Demonstrators with Unknown Biases

no code implementations • ICLR 2019 • Rohin Shah, Noah Gundotra, Pieter Abbeel, Anca Dragan

Our goal is to infer reward functions from demonstrations.

On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference

no code implementations • 23 Jun 2019 • Rohin Shah, Noah Gundotra, Pieter Abbeel, Anca D. Dragan

But in the era of deep learning, a natural suggestion researchers make is to avoid mathematical models of human behavior that are fraught with specific assumptions, and instead use a purely data-driven approach.