Data-Efficient Hierarchical Goal-Conditioned Reinforcement Learning via Normalizing Flows

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Garg, Shaswat, Moezzi, Matin, Da Silva, Brandon
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917268410073088
author Garg, Shaswat
Moezzi, Matin
Da Silva, Brandon
author_facet Garg, Shaswat
Moezzi, Matin
Da Silva, Brandon
contents Hierarchical goal-conditioned reinforcement learning (H-GCRL) provides a powerful framework for tackling complex, long-horizon tasks by decomposing them into structured subgoals. However, its practical adoption is hindered by poor data efficiency and limited policy expressivity, especially in offline or data-scarce regimes. In this work, Normalizing flow-based hierarchical implicit Q-learning (NF-HIQL), a novel framework that replaces unimodal gaussian policies with expressive normalizing flow policies at both the high- and low-levels of the hierarchy is introduced. This design enables tractable log-likelihood computation, efficient sampling, and the ability to model rich multimodal behaviors. New theoretical guarantees are derived, including explicit KL-divergence bounds for Real-valued non-volume preserving (RealNVP) policies and PAC-style sample efficiency results, showing that NF-HIQL preserves stability while improving generalization. Empirically, NF-HIQL is evaluted across diverse long-horizon tasks in locomotion, ball-dribbling, and multi-step manipulation from OGBench. NF-HIQL consistently outperforms prior goal-conditioned and hierarchical baselines, demonstrating superior robustness under limited data and highlighting the potential of flow-based architectures for scalable, data-efficient hierarchical reinforcement learning.
format Preprint
id arxiv_https___arxiv_org_abs_2602_11142
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Data-Efficient Hierarchical Goal-Conditioned Reinforcement Learning via Normalizing Flows
Garg, Shaswat
Moezzi, Matin
Da Silva, Brandon
Robotics
Artificial Intelligence
Machine Learning
Hierarchical goal-conditioned reinforcement learning (H-GCRL) provides a powerful framework for tackling complex, long-horizon tasks by decomposing them into structured subgoals. However, its practical adoption is hindered by poor data efficiency and limited policy expressivity, especially in offline or data-scarce regimes. In this work, Normalizing flow-based hierarchical implicit Q-learning (NF-HIQL), a novel framework that replaces unimodal gaussian policies with expressive normalizing flow policies at both the high- and low-levels of the hierarchy is introduced. This design enables tractable log-likelihood computation, efficient sampling, and the ability to model rich multimodal behaviors. New theoretical guarantees are derived, including explicit KL-divergence bounds for Real-valued non-volume preserving (RealNVP) policies and PAC-style sample efficiency results, showing that NF-HIQL preserves stability while improving generalization. Empirically, NF-HIQL is evaluted across diverse long-horizon tasks in locomotion, ball-dribbling, and multi-step manipulation from OGBench. NF-HIQL consistently outperforms prior goal-conditioned and hierarchical baselines, demonstrating superior robustness under limited data and highlighting the potential of flow-based architectures for scalable, data-efficient hierarchical reinforcement learning.
title Data-Efficient Hierarchical Goal-Conditioned Reinforcement Learning via Normalizing Flows
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2602.11142