Understanding Reward Ambiguity Through Optimal Transport Theory in Inverse Reinforcement Learning
This addresses robustness issues in IRL for applications like robotics and autonomous systems, though it is incremental as it builds on existing OT theory.
The paper tackled the problem of reward ambiguity in inverse reinforcement learning, where multiple reward functions can explain expert behaviors, by using optimal transport theory to quantify ambiguity and identify central reward representations, resulting in a geometric framework for robust methods in high-dimensional settings.
In inverse reinforcement learning (IRL), the central objective is to infer underlying reward functions from observed expert behaviors in a way that not only explains the given data but also generalizes to unseen scenarios. This ensures robustness against reward ambiguity where multiple reward functions can equally explain the same expert behaviors. While significant efforts have been made in addressing this issue, current methods often face challenges with high-dimensional problems and lack a geometric foundation. This paper harnesses the optimal transport (OT) theory to provide a fresh perspective on these challenges. By utilizing the Wasserstein distance from OT, we establish a geometric framework that allows for quantifying reward ambiguity and identifying a central representation or centroid of reward functions. These insights pave the way for robust IRL methodologies anchored in geometric interpretations, offering a structured approach to tackle reward ambiguity in high-dimensional settings.