paper-with-me

Papers

SaFormer: A Conditional Sequence Modeling Approach to Offline Safe Reinforcement Learning

2023-01-28 · Qin Zhang, Linrui Zhang, Haoran Xu, Li Shen, Bowen Wang, Yongzhe Chang, Xueqian Wang, Bo Yuan, DaCheng Tao

Offline safe RL is of great practical relevance for deploying agents in real-world applications. However, acquiring constraint-satisfying policies from the fixed dataset is non-trivial for conventional approaches. Even worse, the learned constraints are stationary and may become invalid when the online safety requirement changes. In this paper, we present a novel offline safe RL approach referred to as SaFormer, which tackles the above issues via conditional sequence modeling. In contrast to existing sequence models, we propose cost-related tokens to restrict the action space and a posterior safety verification to enforce the constraint explicitly. Specifically, SaFormer performs a two-stage auto-regression conditioned by the maximum remaining cost to generate feasible candidates. It then filters out unsafe attempts and executes the optimal action with the highest expected return. Extensive experiments demonstrate the efficacy of SaFormer featuring (1) competitive returns with tightened constraint satisfaction; (2) adaptability to the in-range cost values of the offline data without retraining; (3) generalizability for constraints beyond the current dataset.

📄 PDF Abstract BibTeX arXiv:2301.12203

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement Learning (RL)Safe Reinforcement Learning

Similar Papers 제목 키워드 기반

Conditional Sequence Modeling for Safe Reinforcement Learning

2026-02-09 · Wensong Bai, Chao Zhang, Qihang Xu, Chufan Chen 외 arxiv

Offline safe reinforcement learning (RL) aims to learn policies from a fixed dataset while maximizing performance under cumulative cost constraints. In practice, deployment requirements often vary across scenarios, neces…

Reinforcement Learning

TCSAFormer: Efficient Vision Transformer with Token Compression and Sparse Attention for Medical Image Segmentation

2025-08-06 · Zunhui Xia, Hongxing Li, Libin Lan arxiv

In recent years, transformer-based methods have achieved remarkable progress in medical image segmentation due to their superior ability to capture long-range dependencies. However, these methods typically suffer from tw…

Medical Image SegmentationSemantic Segmentation

OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning

2024-07-19 · Yihang Yao, Zhepeng Cen, Wenhao Ding, Haohong Lin 외

Offline safe reinforcement learning (RL) aims to train a policy that satisfies constraints using a pre-collected dataset. Most current methods struggle with the mismatch between imperfect demonstrations and the desired s…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Reinforcement Learning

RSAFormer: A method of polyp segmentation with region self-attention transformer

2024-04-01 · Computers in Biology and Medicine 2024 4 · Xuehui Yin, Jun Zeng, Tianxiao Hou, Chao Tang 외

Colonoscopy has attached great importance to early screening and clinical diagnosis of colon cancer. It remains a challenging task to achieve fine segmentation of polyps. However, existing State-of-the-art models still h…

DecoderMedical Image Segmentation

Robust Decision Transformer: Tackling Data Corruption in Offline RL via Sequence Modeling

2024-07-05 · Jiawei Xu, Rui Yang, Feng Luo, Meng Fang 외

Learning policies from offline datasets through offline reinforcement learning (RL) holds promise for scaling data-driven decision-making and avoiding unsafe and costly online interactions. However, real-world data colle…

Offline RLReinforcement Learning (RL)