paper-with-me

Papers

Stitching Sub-Trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL

2024-02-11 · Sungyoon Kim, Yunseon Choi, Daiki E. Matsunaga, Kee-Eung Kim

Offline Goal-Conditioned Reinforcement Learning (Offline GCRL) is an important problem in RL that focuses on acquiring diverse goal-oriented skills solely from pre-collected behavior datasets. In this setting, the reward feedback is typically absent except when the goal is achieved, which makes it difficult to learn policies especially from a finite dataset of suboptimal behaviors. In addition, realistic scenarios involve long-horizon planning, which necessitates the extraction of useful skills within sub-trajectories. Recently, the conditional diffusion model has been shown to be a promising approach to generate high-quality long-horizon plans for RL. However, their practicality for the goal-conditioned setting is still limited due to a number of technical assumptions made by the methods. In this paper, we propose SSD (Sub-trajectory Stitching with Diffusion), a model-based offline GCRL method that leverages the conditional diffusion model to address these limitations. In summary, we use the diffusion model that generates future plans conditioned on the target goal and value, with the target value estimated from the goal-relabeled offline dataset. We report state-of-the-art performance in the standard benchmark set of GCRL tasks, and demonstrate the capability to successfully stitch the segments of suboptimal trajectories in the offline data to generate high-quality plans.

📄 PDF Abstract BibTeX arXiv:2402.07226

Code (1)

rlatjddbs/ssd 공식 구현 pytorch

Tasks

Offline RL

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Non Maximum Suppression Non Maximum Suppression is a computer vision method that selects a single entity out of many overlapping entities (for example bounding boxes in object detection). The…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
SSD SSD is a single-stage object detection method that discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per…

Similar Papers 제목 키워드 기반

What Do You Need for Diverse Trajectory Stitching in Diffusion Planning?

2025-05-23 · Quentin Clark, Florian Shkurti

In planning, stitching is an ability of algorithms to piece together sub-trajectories of data they are trained on to generate new and diverse behaviours. While stitching is historically a strength of offline reinforcemen…

Behavioural cloningData Augmentation

GAS: Enhancing Reward-Cost Balance of Generative Model-assisted Offline Safe RL

2026-02-05 · Zifan Liu, Xinran Li, Shibo Chen, Jun Zhang arxiv

Offline Safe Reinforcement Learning (OSRL) aims to learn a policy to achieve high performance in sequential decision-making while satisfying constraints, using only pre-collected datasets. Recent works, inspired by the s…

Reinforcement Learning

QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL

2026-05-03 · Xing Lei, Jincheng Wang, Xuetao Zhang, Donglin Wang arxiv

Offline goal-conditioned RL (GCRL) learns goal-reaching policies from static datasets, but real-world datasets are often partially observable and history-dependent, exhibiting a mix of Markovian and non-Markovian that vi…

Efficient Virtuoso: A Latent Diffusion Transformer Model for Goal-Conditioned Trajectory Planning

2025-09-03 · Antonio Guillen-Perez arxiv

The ability to generate a diverse and plausible distribution of future trajectories is a critical capability for autonomous vehicle planning systems. While recent generative models have shown promise, achieving high fide…

Computational EfficiencyTrajectory Planning

DiffStitch: Boosting Offline Reinforcement Learning with Diffusion-based Trajectory Stitching

2024-02-04 · Guanghe Li, Yixiang Shan, Zhengbang Zhu, Ting Long 외

In offline reinforcement learning (RL), the performance of the learned policy highly depends on the quality of offline datasets. However, in many cases, the offline dataset contains very limited optimal trajectories, whi…

D4RLData AugmentationImitation LearningOffline RL+2