PVEs: Position-Velocity Encoders for Unsupervised Learning of Structured State Representations
Not on the map. Why?
Abstract (arXiv)
We propose position-velocity encoders (PVEs) which learn---without supervision---to encode images to positions and velocities of task-relevant objects. PVEs encode a single image into a low-dimensional position state and compute the velocity state from finite differences in position. In contrast to autoencoders, position-velocity encoders are not trained by image reconstruction, but by making the position-velocity representation consistent with priors about interacting with the physical world. We applied PVEs to several simulated control tasks from pixels and achieved promising preliminary results.
Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). First posted on arXiv 27 May 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2019: 1; 2020: 0; 2021: 4; 2022: 7; 2023: 1; 2024: 2; 2025: 1.
16 papers.
Sort:
By area:
- 2022Reinforcement Learning with Neural Radiance Fieldscited by 43
- 2022Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learningcited by 38
- 2023Lossless Adaptation of Pretrained Vision Models For Robotic Manipulationcited by 29
- 2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Reviewcited by 18
- 2025A Survey of State Representation Learning for Deep Reinforcement Learningcited by 17
- 2022Learning on the Job: Self-Rewarding Offline-to-Online Finetuning for Industrial Insertion of Novel Connectors from Visioncited by 13
- 2024Reinforcement Learning with Generalizable Gaussian Splattingcited by 13
- 2022Integrating Contrastive Learning with Dynamic Models for Reinforcement Learning from Imagescited by 12
- 2021Low Dimensional State Representation Learning with Robotics Priors in Continuous Action Spacescited by 9
- 2019State Representation Learning from Demonstrationcited by 5
- 2024MOOSS: Mask-Enhanced Temporal Contrastive Learning for Smooth State Evolution in Visual Reinforcement Learningcited by 3
- 2021Low-Dimensional State and Action Representation Learning with MDP Homomorphism Metricscited by 2
4 more
- 2022Distilling Governing Laws and Source Input for Dynamical Systems from Videoscited by 2
- 2021Uncovering Closed-form Governing Equations of Nonlinear Dynamics from Videoscited by 1
- 2021Learn Proportional Derivative Controllable Latent Space from Pixelscited by 0
- 2022Locally Constrained Representations in Reinforcement Learningcited by 0
- 2025A Survey of State Representation Learning for Deep Reinforcement Learning20 Jun 2025
- 2024MOOSS: Mask-Enhanced Temporal Contrastive Learning for Smooth State Evolution in Visual Reinforcement Learning2 Sep 2024
- 2024Reinforcement Learning with Generalizable Gaussian Splatting18 Mar 2024
- 2023Lossless Adaptation of Pretrained Vision Models For Robotic Manipulation13 Apr 2023
- 2022Learning on the Job: Self-Rewarding Offline-to-Online Finetuning for Industrial Insertion of Novel Connectors from Vision27 Oct 2022
- 2022Locally Constrained Representations in Reinforcement Learning20 Sep 2022
- 2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Review27 Aug 2022
- 2022Reinforcement Learning with Neural Radiance Fields3 Jun 2022
- 2022Distilling Governing Laws and Source Input for Dynamical Systems from Videos3 May 2022
- 2022Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning27 Apr 2022
- 2022Integrating Contrastive Learning with Dynamic Models for Reinforcement Learning from Images2 Mar 2022
- 2021Learn Proportional Derivative Controllable Latent Space from Pixels15 Oct 2021
4 more
- 2021Low-Dimensional State and Action Representation Learning with MDP Homomorphism Metrics4 Jul 2021
- 2021Low Dimensional State Representation Learning with Robotics Priors in Continuous Action Spaces4 Jul 2021
- 2021Uncovering Closed-form Governing Equations of Nonlinear Dynamics from Videos9 Jun 2021
- 2019State Representation Learning from Demonstration15 Sep 2019
- 2019State Representation Learning from Demonstrationcited by 5
- 2019State Representation Learning from Demonstration15 Sep 2019
- 2022Reinforcement Learning with Neural Radiance Fieldscited by 43
- 2022Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learningcited by 38
- 2023Lossless Adaptation of Pretrained Vision Models For Robotic Manipulationcited by 29
- 2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Reviewcited by 18
- 2022Integrating Contrastive Learning with Dynamic Models for Reinforcement Learning from Imagescited by 12
- 2021Low Dimensional State Representation Learning with Robotics Priors in Continuous Action Spacescited by 9
- 2021Low-Dimensional State and Action Representation Learning with MDP Homomorphism Metricscited by 2
- 2022Distilling Governing Laws and Source Input for Dynamical Systems from Videoscited by 2
- 2021Uncovering Closed-form Governing Equations of Nonlinear Dynamics from Videoscited by 1
- 2021Learn Proportional Derivative Controllable Latent Space from Pixelscited by 0
- 2022Locally Constrained Representations in Reinforcement Learningcited by 0
- 2023Lossless Adaptation of Pretrained Vision Models For Robotic Manipulation13 Apr 2023
- 2022Locally Constrained Representations in Reinforcement Learning20 Sep 2022
- 2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Review27 Aug 2022
- 2022Reinforcement Learning with Neural Radiance Fields3 Jun 2022
- 2022Distilling Governing Laws and Source Input for Dynamical Systems from Videos3 May 2022
- 2022Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning27 Apr 2022
- 2022Integrating Contrastive Learning with Dynamic Models for Reinforcement Learning from Images2 Mar 2022
- 2021Learn Proportional Derivative Controllable Latent Space from Pixels15 Oct 2021
- 2021Low-Dimensional State and Action Representation Learning with MDP Homomorphism Metrics4 Jul 2021
- 2021Low Dimensional State Representation Learning with Robotics Priors in Continuous Action Spaces4 Jul 2021
- 2021Uncovering Closed-form Governing Equations of Nonlinear Dynamics from Videos9 Jun 2021