Multi-Horizon Representations with Hierarchical Forward Models for Reinforcement Learning

TL;DR

This paper introduces HKSL, a hierarchical multi-step auxiliary task for reinforcement learning from pixels, which improves learning efficiency and representation quality across multiple timescales in robotic control tasks.

Contribution

HKSL is a novel hierarchical approach that learns multi-scale representations using forward models and ensemble critics, addressing temporal challenges in pixel-based RL.

Findings

HKSL converges faster to higher or optimal returns than alternative methods.

HKSL's representations accurately capture task-relevant details across timescales.

Communication between hierarchy levels organizes information effectively, enhancing sample efficiency.

Abstract

Learning control from pixels is difficult for reinforcement learning (RL) agents because representation learning and policy learning are intertwined. Previous approaches remedy this issue with auxiliary representation learning tasks, but they either do not consider the temporal aspect of the problem or only consider single-step transitions, which may cause learning inefficiencies if important environmental changes take many steps to manifest. We propose Hierarchical $k$-Step Latent (HKSL), an auxiliary task that learns multiple representations via a hierarchy of forward models that learn to communicate and an ensemble of $n$-step critics that all operate at varying magnitudes of step skipping. We evaluate HKSL in a suite of 30 robotic control tasks with and without distractors and a task of our creation. We find that HKSL either converges to higher or optimal episodic returns more quickly than several alternative representation learning approaches. Furthermore, we find that HKSL's representations capture task-relevant details accurately across timescales (even in the presence of distractors) and that communication channels between hierarchy levels organize information based on both sides of the communication process, both of which improve sample efficiency.