Erik Jenner

STARC (STAndardised Reward Comparison) metrics, a class of pseudometrics, quantify differences between reward functions, providing theoretical and empirical tools to improve the analysis and safety of reward learning algorithms in reinforcement learning.

We describe a software package called "imitation" which provides PyTorch implementations of several imitation and reward learning algorithms, including three inverse reinforcement learning algorithms, three imitation learning algorithms, and a preference comparison algorithm.