Salvato in:
Dettagli Bibliografici
Autori principali: Lee, Dongsu, Kwon, Minhae
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2505.13144
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912382172790784
author Lee, Dongsu
Kwon, Minhae
author_facet Lee, Dongsu
Kwon, Minhae
contents The goal of offline reinforcement learning (RL) is to extract a high-performance policy from the fixed datasets, minimizing performance degradation due to out-of-distribution (OOD) samples. Offline model-based RL (MBRL) is a promising approach that ameliorates OOD issues by enriching state-action transitions with augmentations synthesized via a learned dynamics model. Unfortunately, seminal offline MBRL methods often struggle in sparse-reward, long-horizon tasks. In this work, we introduce a novel MBRL framework, dubbed Temporal Distance-Aware Transition Augmentation (TempDATA), that generates augmented transitions in a temporally structured latent space rather than in raw state space. To model long-horizon behavior, TempDATA learns a latent abstraction that captures a temporal distance from both trajectory and transition levels of state space. Our experiments confirm that TempDATA outperforms previous offline MBRL methods and achieves matching or surpassing the performance of diffusion-based trajectory augmentation and goal-conditioned RL on the D4RL AntMaze, FrankaKitchen, CALVIN, and pixel-based FrankaKitchen.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13144
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement Learning
Lee, Dongsu
Kwon, Minhae
Machine Learning
Artificial Intelligence
Robotics
The goal of offline reinforcement learning (RL) is to extract a high-performance policy from the fixed datasets, minimizing performance degradation due to out-of-distribution (OOD) samples. Offline model-based RL (MBRL) is a promising approach that ameliorates OOD issues by enriching state-action transitions with augmentations synthesized via a learned dynamics model. Unfortunately, seminal offline MBRL methods often struggle in sparse-reward, long-horizon tasks. In this work, we introduce a novel MBRL framework, dubbed Temporal Distance-Aware Transition Augmentation (TempDATA), that generates augmented transitions in a temporally structured latent space rather than in raw state space. To model long-horizon behavior, TempDATA learns a latent abstraction that captures a temporal distance from both trajectory and transition levels of state space. Our experiments confirm that TempDATA outperforms previous offline MBRL methods and achieves matching or surpassing the performance of diffusion-based trajectory augmentation and goal-conditioned RL on the D4RL AntMaze, FrankaKitchen, CALVIN, and pixel-based FrankaKitchen.
title Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement Learning
topic Machine Learning
Artificial Intelligence
Robotics
url https://arxiv.org/abs/2505.13144