Extendable Long-Horizon Planning via Hierarchical Multiscale Diffusion
This paper tackles a novel problem, extendable long-horizon planning-enabling agents to plan trajectories longer than those in training data without compounding errors. To tackle this, we propose the Hierarchical Multiscale Diffuser (HM-Diffuser) and Progressive Trajectory Extension (PTE), an augmentation method that iteratively generates longer trajectories by stitching shorter ones. HM-Diffuser trains on these extended trajectories using a hierarchical structure, efficiently handling tasks across multiple temporal scales. Additionally, we introduce Adaptive Plan Pondering and the Recursive HM-Diffuser, which consolidate hierarchical layers into a single model to process temporal scales recursively. Experimental results demonstrate the effectiveness of our approach, advancing diffusion-based planners for scalable long-horizon planning.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Hierarchical Planning with Latent World Models
World models are a promising path to zero-shot embodied control through planning. However, existing world model planners struggle on long-horizon, multi-stage tasks: prediction errors compound and naive search is exponen…
HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning
While Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents across a wide range of tasks, their performance often degrades in multi-turn long-horizon agentic tasks. Existing methods have…
Hierarchical Reinforcement LearningStrict Subgoal Execution: Reliable Long-Horizon Planning in Hierarchical Reinforcement Learning
Long-horizon goal-conditioned tasks pose fundamental challenges for reinforcement learning (RL), particularly when goals are distant and rewards are sparse. While hierarchical and graph-based methods offer partial soluti…
Decision MakingHierarchical Reinforcement LearningReinforcement Learning (RL)Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors
The ability to predict and plan into the future is fundamental for agents acting in the world. To reach a faraway goal, we predict trajectories at multiple timescales, first devising a coarse plan towards the goal and th…
PredictionH-WM: Robotic Task and Motion Planning Guided by Hierarchical World Model
World models are becoming central to robotic planning and control as they enable prediction of future state transitions. Existing approaches often emphasize video generation or natural-language prediction, which are diff…
Visual GroundingVideo GenerationMotion Planning