Plan2Vec: Unsupervised Representation Learning by Latent Plans
In this paper we introduce plan2vec, an unsupervised representation learning approach that is inspired by reinforcement learning. Plan2vec constructs a weighted graph on an image dataset using near-neighbor distances, and then extrapolates this local metric to a global embedding by distilling path-integral over planned path. When applied to control, plan2vec offers a way to learn goal-conditioned value estimates that are accurate over long horizons that is both compute and sample efficient. We demonstrate the effectiveness of plan2vec on one simulated and two challenging real-world image datasets. Experimental results show that plan2vec successfully amortizes the planning cost, enabling reactive planning that is linear in memory and computation complexity rather than exhaustive over the entire state space.
Code (1)
Tasks
Motion Planningreinforcement-learningReinforcement Learning (RL)Representation LearningSimilar Papers 제목 키워드 기반
Latent Space Arc Therapy Optimization
Volumetric modulated arc therapy planning is a challenging problem in high-dimensional, non-convex optimization. Traditionally, heuristics such as fluence-map-optimization-informed segment initialization use locally opti…
ARCiCLP: Large Language Model Reasoning with Implicit Cognition Latent Planning
Large language models (LLMs), when guided by explicit textual plans, can perform reliable step-by-step reasoning during problem-solving. However, generating accurate and effective textual plans remains challenging due to…
Mathematical ReasoningDomain GeneralizationCode GenerationGrounding Generated Videos in Feasible Plans via World Models
Large-scale video generative models have shown emerging capabilities as zero-shot visual planners, yet video-generated plans often violate temporal consistency and physical constraints, leading to failures when mapped to…
Unit Region Encoding: A Unified and Compact Geometry-aware Representation for Floorplan Applications
We present the Unit Region Encoding of floorplans, which is a unified and compact geometry-aware encoding representation for various applications, ranging from interior space planning, floorplan metric learning to floorp…
Metric LearningBilevel Planning with Learned Symbolic Abstractions from Interaction Data
Intelligent agents must reason over both continuous dynamics and discrete representations to generate effective plans in complex environments. Previous studies have shown that symbolic abstractions can emerge from neural…