mlsanityData to 14 Oct 2026

Sparse Representation Learning with Modified q-VAE towards Minimal Realization of World Model

arXiv 2208.03936 ↗First posted 8 Aug 2022cs.LG cs.ROcited by 1

On the map: World models → Embodied and robot world models

Abstract (arXiv)

Extraction of low-dimensional latent space from high-dimensional observation data is essential to construct a real-time robot controller with a world model on the extracted latent space. However, there is no established method for tuning the dimension size of the latent space automatically, suffering from finding the necessary and sufficient dimension size, i.e. the minimal realization of the world model. In this study, we analyze and improve Tsallis-based variational autoencoder (q-VAE), and reveal that, under an appropriate configuration, it always facilitates making the latent space sparse. Even if the dimension size of the pre-specified latent space is redundant compared to the minimal realization, this sparsification collapses unnecessary dimensions, allowing for easy removal of them. We experimentally verified the benefits of the sparsification by the proposed method that it can easily find the necessary and sufficient six dimensions for a reaching task with a mobile manipulator that requires a six-dimensional state space. Moreover, by planning with such a minimal-realization world model learned in the extracted dimensions, the proposed method was able to exert a more optimal action sequence in real-time, reducing the reaching accomplishment time by around 20 %. The attached video is uploaded on youtube: https://youtu.be/-QjITrnxaRs

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Embodied and robot world models, one of 11 directions in World models. Builds on 25 of its 44 references that are in the map. First posted on arXiv 8 Aug 2022.

Builds on

25 of 44 references.

References · 25

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Layer Normalizationcited by 5,669
  3. 2013Auto-Encoding Variational Bayescited by 4,053
  4. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  5. 2018World Modelscited by 1,513
  6. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
  7. 2020Mastering Atari with Discrete World Modelscited by 1,007
  8. 2017Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learningcited by 950
  9. 2018Towards a Definition of Disentangled Representationscited by 296
  10. 2017Automated Curriculum Learning for Neural Networkscited by 257
  11. 2016A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehiclescited by 254
  12. 2019Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Modelcited by 231
13 more
  1. 2018State Representation Learning for Control: An Overviewcited by 127
  2. 2017Information Theoretic Model Predictive Control: Theory and Applications to Autonomous Drivingcited by 90
  3. 2020Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstructioncited by 66
  4. 2016Improving Variational Auto-Encoders using Householder Flowcited by 42
  5. 2019The continuous Bernoulli: fixing a pervasive error in variational autoencoderscited by 41
  6. 2021The Design of Stretch: A Compact, Lightweight Mobile Manipulator for Indoor Human Environmentscited by 40
  7. 2019Variational Inference MPC for Bayesian Model-based Reinforcement Learningcited by 39
  8. 2018Variational Autoencoder with Implicit Optimal Priorscited by 33
  9. 2020PlaNet of the Bayesians: Reconsidering and Improving Deep Planning Network by Incorporating Bayesian Inferencecited by 23
  10. 2020NewtonianVAE: Proportional Control and Goal Identification from Pixels via Physical Latent Spacescited by 15
  11. 2020q-VAE for Disentangled Representation Learning and Latent Dynamical Systemscited by 9
  12. 2022Tactile-Sensitive NewtonianVAE for High-Accuracy Industrial Connector Insertioncited by 3
  13. 2021Latent Representation in Human-Robot Interaction with Explicit Consideration of Periodic Dynamicscited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024LiRA: Light-Robust Adversary for Model-based Reinforcement Learning in Real Worldcited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2019Goal-Conditioned Variational Autoencoder Trajectory Primitives with Continuous and Discrete Latent Codes
  2. 2022Efficient Planning in a Compact Latent Action Space
  3. 2023SC-VAE: Sparse Coding-based Variational Autoencoder with Learned ISTA
  4. 2026EmbodiedVAE: Disentangled Video VAE for Efficient and Controllable Embodied Manipulation
  5. 2023Learning Sampling Dictionaries for Efficient and Generalizable Robot Motion Planning with Transformers
  6. 2026Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models
  7. 2026P3: Probabilistic Policy Propagation for Stable VAE-Based Robot Learning ↗
  8. 2025Bounding Distributional Shifts in World Modeling through Novelty Detection