Diffstitch: Boosting Offline Reinforcement Learning With Diffusion-based Trajectory Stitching

Abstract

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, which poses a challenge for offline RL algorithms as agents must acquire the ability to transit to high-reward regions. To address this issue, we introduce Diffusion-based Trajectory Stitching (DiffStitch), a novel diffusion-based data augmentation pipeline that systematically generates stitching transitions between trajectories. DiffStitch effectively connects low-reward trajectories with high-reward trajectories, forming globally optimal trajectories to address the challenges faced by offline RL algorithms. Empirical experiments conducted on D4RL datasets demonstrate the effectiveness of DiffStitch across RL methodologies. Notably, DiffStitch demonstrates substantial enhancements in the performance of one-step methods (IQL), imitation learning methods (TD3+BC), and traje

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyli2024diffstitch

Related papers

• Model-based Trajectory Stitching For Improved Offline Reinforcement Learning (2022)0.00
• Atradiff: Accelerating Online Reinforcement Learning With Imaginary Trajectories (2024)0.00
• Bitrajdiff: Bidirectional Trajectory Generation With Diffusion Models For Offline Reinforcement Learning (2025)0.00
• Contrastive Diffuser: Planning Towards High Return States Via Contrastive Learning (2024)0.00
• Diffusion Policies Creating A Trust Region For Offline Reinforcement Learning (2024)8.04
• Offline RL With Observation Histories: Analyzing And Improving Sample Complexity (2023)0.00
• Preferred-action-optimized Diffusion Policies For Offline Reinforcement Learning (2024)0.00
• BATS: Best Action Trajectory Stitching (2022)0.00