PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation

TL;DR

PEARL introduces a zero-shot transfer method for preference-based reinforcement learning in robotics, aligning preferences across tasks using optimal transport and robust reward modeling, reducing reliance on human labels.

Contribution

The paper presents a novel zero-shot transfer framework combining preference alignment via Gromov-Wasserstein and robust reward learning, enabling effective policy learning without target task labels.

Findings

Outperforms existing methods with limited human preferences

Accurately transfers preferences across diverse tasks

Learns well-behaved policies in robotic manipulation

Abstract

In preference-based Reinforcement Learning (RL), obtaining a large number of preference labels are both time-consuming and costly. Furthermore, the queried human preferences cannot be utilized for the new tasks. In this paper, we propose Zero-shot Cross-task Preference Alignment and Robust Reward Learning (PEARL), which learns policies from cross-task preference transfer without any human labels of the target task. Our contributions include two novel components that facilitate the transfer and learning process. The first is Cross-task Preference Alignment (CPA), which transfers the preferences between tasks via optimal transport. The key idea of CPA is to use Gromov-Wasserstein distance to align the trajectories between tasks, and the solved optimal transport matrix serves as the correspondence between trajectories. The target task preferences are computed as the weighted sum of source task preference labels with the correspondence as weights. Moreover, to ensure robust learning from these transferred labels, we introduce Robust Reward Learning (RRL), which considers both reward mean and uncertainty by modeling rewards as Gaussian distributions. Empirical results on robotic manipulation tasks from Meta-World and Robomimic demonstrate that our method is capable of transferring preference labels across tasks accurately and then learns well-behaved policies. Notably, our approach significantly exceeds existing methods when there are few human preferences. The code and videos of our method are available at: https://sites.google.com/view/pearl-preference.