Sparse Diffusion Policy: A Sparse, Reusable, And Flexible Policy For Robot Learning

Abstract

The increasing complexity of tasks in robotics demands efficient strategies for multitask and continual learning. Traditional models typically rely on a universal policy for all tasks, facing challenges such as high computational costs and catastrophic forgetting when learning new tasks. To address these issues, we introduce a sparse, reusable, and flexible policy, Sparse Diffusion Policy (SDP). By adopting Mixture of Experts (MoE) within a transformer-based diffusion policy, SDP selectively activates experts and skills, enabling efficient and task-specific learning without retraining the entire model. SDP not only reduces the burden of active parameters but also facilitates the seamless integration and reuse of experts across various tasks. Extensive experiments on diverse tasks in both simulations and real world show that SDP 1) excels in multitask scenarios with negligible increases in active parameters, 2) prevents forgetting in continual learning of new tasks, and 3) enables effic

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywang2024sparse

Related papers

• Streaming Diffusion Policy: Fast Policy Synthesis With Variable Noise Diffusion Models (2024)0.00
• Delay-aware Diffusion Policy: Bridging The Observation-execution Gap In Dynamic Tasks (2025)0.00
• Equivariant Diffusion Policy (2024)0.00
• Multi-objective Model-based Policy Search For Data-efficient Learning With Sparse Rewards (2018)0.00
• Fine-tuning Diffusion Policies With Backpropagation Through Diffusion Timesteps (2025)0.00
• Steering Your Diffusion Policy With Latent Space Reinforcement Learning (2025)0.00
• Probabilistic Mixture-of-experts For Efficient Deep Reinforcement Learning (2021)0.00
• Diffusion Policy With Bayesian Expert Selection For Active Multi-target Tracking (2026)0.00