2019
On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference
ICML 2019oral
Our goal is for agents to optimize the right reward function, despite how difficult it is for us to specify what that is. Inverse Reinforcement Learning (IRL) enables us to infer reward functions from demonstrations, but it usually assumes that the expert is noisily optimal. Real people, on the othe…