# Plan2Vec: Unsupervised Representation Learning by Latent Plans

arXiv: https://arxiv.org/abs/2005.03648 · HTML: https://mlsanity.com/paper/2005.03648/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2020.

## Built on by (most cited first, 21 of 21)

- [Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning](https://mlsanity.com/paper/2304.01203/) (2023)
- [Making Linear MDPs Practical via Contrastive Representation Learning](https://mlsanity.com/paper/2207.07150/) (2022)
- [Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2204.13060/) (2022)
- [Temporal Straightening for Latent Planning](https://mlsanity.com/paper/2603.12231/) (2026)
- [Investigating the Properties of Neural Network Representations in Reinforcement Learning](https://mlsanity.com/paper/2203.15955/) (2022)
- [Unsupervised Representation Learning in Deep Reinforcement Learning: A Review](https://mlsanity.com/paper/2208.14226/) (2022)
- [Reducing Collision Checking for Sampling-Based Motion Planning Using Graph Neural Networks](https://mlsanity.com/paper/2210.08864/) (2022)
- [DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs](https://mlsanity.com/paper/2010.08891/) (2020)
- [Transformers are Adaptable Task Planners](https://mlsanity.com/paper/2207.02442/) (2022)
- [Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning](https://mlsanity.com/paper/2206.04384/) (2022)
- [One-4-All: Neural Potential Fields for Embodied Navigation](https://mlsanity.com/paper/2303.04011/) (2023)
- [Neural Constraint Satisfaction: Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement](https://mlsanity.com/paper/2303.11373/) (2023)
- [Offline Goal-Conditioned Reinforcement Learning with Projective Quasimetric Planning](https://mlsanity.com/paper/2506.18847/) (2025)
- [Goal-Conditioned Reinforcement Learning from Sub-Optimal Data on Metric Spaces](https://mlsanity.com/paper/2402.10820/) (2024)
- [Guided Cooperation in Hierarchical Reinforcement Learning via Model-based Rollout](https://mlsanity.com/paper/2309.13508/) (2023)
- [Entropy-driven Unsupervised Keypoint Representation Learning in Videos](https://mlsanity.com/paper/2209.15404/) (2022)
- [Spectral Temporal Contrastive Learning](https://mlsanity.com/paper/2312.00966/) (2023)
- [Physics-informed Goal-Conditioned Reinforcement Learning under Hybrid Contact Dynamics](https://mlsanity.com/paper/2605.30503/) (2026)
- [Compact Bellman-Grounded Cognitive Maps for Cost-Aware Navigation](https://mlsanity.com/paper/2609.05104/) (2026)
- [Metro-WM: Long-Horizon Latent Planning with Realisable Sub-Goals](https://mlsanity.com/paper/2609.31868/) (2026)
- [Learning Goal-Reaching Quasimetric Geometry From Finite-Time Reachability](https://mlsanity.com/paper/2610.00778/) (2026)

## 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.