Abstraction for Offline Goal-Conditioned Reinforcement Learning

TL;DR

This paper introduces a hierarchical abstraction framework for offline goal-conditioned reinforcement learning, leveraging relativised options to improve experience reuse and performance.

Contribution

It proposes a novel hierarchy-based abstraction method with relativised options and demonstrates its effectiveness through two new algorithms.

Findings

Hierarchical abstraction improves offline GCRL performance.

Relativised options enable better experience reuse across contexts.

Algorithms based on this framework outperform baselines in experiments.

Abstract

Markov Decision Processes (MDPs) often exhibit significant redundancy due to symmetries and shared structure across state-goal pairs in real-world Goal-Conditioned Reinforcement Learning (GCRL). While hierarchical policies have been motivated for horizon reduction via temporal abstraction in offline GCRL, we demonstrate that hierarchy also enables absolute abstraction. By introducing relativised options as well as distinct representations for different levels of the hierarchy, we demonstrate how an agent can reuse experience across similar contexts of the state-space. Based on this framework, we introduce two simple algorithms for learning relativised options and abstracting from the absolute frame of reference. Our experiments show that such inductive biases significantly improve performance in offline GCRL.