Generative Trajectory Stitching through Diffusion Composition
Effective trajectory stitching for long-horizon planning is a significant challenge in robotic decision-making. While diffusion models have shown promise in planning, they are limited to solving tasks similar to those seen in their training data. We propose CompDiffuser, a novel generative approach that can solve new tasks by learning to compositionally stitch together shorter trajectory chunks from previously seen tasks. Our key insight is modeling the trajectory distribution by subdividing it into overlapping chunks and learning their conditional relationships through a single bidirectional diffusion model. This allows information to propagate between segments during generation, ensuring physically consistent connections. We conduct experiments on benchmark tasks of various difficulties, covering different environment sizes, agent state dimension, trajectory types, training data quality, and show that CompDiffuser significantly outperforms existing methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
What Do You Need for Diverse Trajectory Stitching in Diffusion Planning?
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 AugmentationEnergy-based Compositional Diffusion Planning
Compositional diffusion planners aim to solve long-horizon robotic tasks using short training trajectories. Yet, current approaches often rely on the heuristic stitching of local predictions. We show that the resulting s…
Generative View Stitching
Autoregressive video diffusion models are capable of long rollouts that are stable and consistent with history, but they are unable to guide the current generation with conditioning from the future. In camera-guided vide…
Video GenerationDiffStitch: Boosting Offline Reinforcement Learning with Diffusion-based Trajectory Stitching
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+2STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation
Off-policy evaluation (OPE) estimates the performance of a target policy using offline data collected from a behavior policy, and is crucial in domains such as robotics or healthcare where direct interaction with the env…
D4RLDenoisingOff-policy evaluationOpenAI Gym