mlsanityData to 7 Oct 2026

Plan2Vec: Unsupervised Representation Learning by Latent Plans

arXiv 2005.03648 ↗First posted 7 May 2020cs.LG cs.AI stat.MLcited by 21

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 0; 2022: 8; 2023: 5; 2024: 1; 2025: 1; 2026: 5.

21 papers.

Sort:

By area:

  1. 2023Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learningcited by 116
  2. 2022Making Linear MDPs Practical via Contrastive Representation Learningcited by 49
  3. 2022Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learningcited by 38
  4. 2026Temporal Straightening for Latent Planningcited by 32
  5. 2022Investigating the Properties of Neural Network Representations in Reinforcement Learningcited by 24
  6. 2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Reviewcited by 18
  7. 2020DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPscited by 16
  8. 2022Reducing Collision Checking for Sampling-Based Motion Planning Using Graph Neural Networkscited by 16
  9. 2022Transformers are Adaptable Task Plannerscited by 15
  10. 2022Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learningcited by 11
  11. 2023One-4-All: Neural Potential Fields for Embodied Navigationcited by 7
  12. 2023Neural Constraint Satisfaction: Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangementcited by 6
9 more
  1. 2025Offline Goal-Conditioned Reinforcement Learning with Projective Quasimetric Planningcited by 5
  2. 2024Goal-Conditioned Reinforcement Learning from Sub-Optimal Data on Metric Spacescited by 3
  3. 2023Guided Cooperation in Hierarchical Reinforcement Learning via Model-based Rolloutcited by 2
  4. 2022Entropy-driven Unsupervised Keypoint Representation Learning in Videoscited by 0
  5. 2023Spectral Temporal Contrastive Learningcited by 0
  6. 2026Physics-informed Goal-Conditioned Reinforcement Learning under Hybrid Contact Dynamicscited by 0
  7. 2026Compact Bellman-Grounded Cognitive Maps for Cost-Aware Navigationcited by 0
  8. 2026Metro-WM: Long-Horizon Latent Planning with Realisable Sub-Goalscited by 0
  9. 2026Learning Goal-Reaching Quasimetric Geometry From Finite-Time Reachabilitycited by 0