mlsanityData to 7 Oct 2026

State Representation Learning for Control: An Overview

arXiv 1802.04181 ↗First posted 12 Feb 2018cs.AI cs.LG stat.MLcited by 125

Not on the map. Why?

Abstract (arXiv)

Representation learning algorithms are designed to learn abstract features that characterize data. State representation learning (SRL) focuses on a particular kind of representation learning where learned features are in low dimension, evolve through time, and are influenced by actions of an agent. The representation is learned to capture the variation in the environment generated by the agent's actions; this kind of representation is particularly suitable for robotics and control scenarios. In particular, the low dimension characteristic of the representation helps to overcome the curse of dimensionality, provides easier interpretation and utilization by humans and can help improve performance and speed in policy learning algorithms such as reinforcement learning. This survey aims at covering the state-of-the-art on state representation learning in the most recent years. It reviews different SRL methods that involve interaction with the environment, their implementations and their applications in robotics control tasks (simulated or real). In particular, it highlights how generic learning objectives are differently exploited in the reviewed algorithms. Finally, it discusses evaluation methods to assess the representation learned and summarizes current and future lines of research.

Key facts. Cited by 125 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 2; 2021: 28; 2022: 20; 2023: 19; 2024: 15; 2025: 23; 2026: 17.

125 papers.

Sort:

By area:

  1. 2023Learning Interactive Real-World Simulatorscited by 440
  2. 2021Pretraining Representations for Data-Efficient Reinforcement Learningcited by 105
  3. 2025TesserAct: Learning 4D Embodied World Modelscited by 90
  4. 2021Learning by Watching: Physical Imitation of Manipulation Skills from Human Videoscited by 87
  5. 2025Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Modelscited by 77
  6. 2022Challenges and Opportunities in Offline Reinforcement Learning from Visual Observationscited by 63
  7. 2023Self-Supervised Multimodal Learning: A Surveycited by 58
  8. 2024Bridging State and History Representations: Understanding Self-Predictive RLcited by 52
  9. 2022Reinforcement Learning with Neural Radiance Fieldscited by 43
  10. 2023BISCUIT: Causal Representation Learning from Binary Interactionscited by 38
  11. 2024Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learningcited by 38
  12. 2021Training Larger Networks for Deep Reinforcement Learningcited by 37
38 more
  1. 2023World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challengescited by 35
  2. 2021Provable Representation Learning for Imitation with Contrastive Fourier Featurescited by 34
  3. 2021Geometric Entropic Explorationcited by 32
  4. 2021Action-Sufficient State Representation Learning for Control with Structural Constraintscited by 31
  5. 2021Learning a State Representation and Navigation in Cluttered and Dynamic Environmentscited by 30
  6. 2021Which Mutual-Information Representation Learning Objectives are Sufficient for Control?cited by 28
  7. 2021JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learningcited by 28
  8. 2024LLM-Empowered State Representation for Reinforcement Learningcited by 28
  9. 2026World-Gymnast: Training Robots with Reinforcement Learning in a World Modelcited by 25
  10. 2022Investigating the Properties of Neural Network Representations in Reinforcement Learningcited by 24
  11. 2021Meta-Adaptive Nonlinear Control: Theory and Algorithmscited by 23
  12. 2021Multimodal VAE Active Inference Controllercited by 21
  13. 2021A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representationcited by 19
  14. 2022Back to the Manifold: Recovering from Out-of-Distribution Statescited by 19
  15. 2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Reviewcited by 18
  16. 2023Concept Learning for Interpretable Multi-Agent Reinforcement Learningcited by 18
  17. 2021Continual Learning in Deep Networks: an Analysis of the Last Layercited by 17
  18. 2023RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictabilitycited by 17
  19. 2025A Survey of State Representation Learning for Deep Reinforcement Learningcited by 17
  20. 2022Reinforcement learning for automatic quadrilateral mesh generation: a soft actor-critic approachcited by 16
  21. 2021Explainable Autonomous Robots: A Survey and Perspectivecited by 15
  22. 2023Testing of Deep Reinforcement Learning Agents with Surrogate Modelscited by 12
  23. 2025Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agentscited by 12
  24. 2023Aligning Robot and Human Representationscited by 11
  25. 2023Transformers in Reinforcement Learning: A Surveycited by 11
  26. 2025Interpretable Machine Learning in Physics: A Reviewcited by 11
  27. 2021Low Dimensional State Representation Learning with Robotics Priors in Continuous Action Spacescited by 9
  28. 2021Common Information based Approximate State Representations in Multi-Agent Reinforcement Learningcited by 8
  29. 2023A Multiagent CyberBattleSim for RL Cyber Operation Agentscited by 8
  30. 2020Domain-Adversarial and Conditional State Space Model for Imitation Learningcited by 7
  31. 2024Parametric PDE Control with Deep Reinforcement Learning and Differentiable L0-Sparse Polynomial Policiescited by 7
  32. 2020Modelling Agent Policies with Interpretable Imitation Learningcited by 6
  33. 2021How to Sense the World: Leveraging Hierarchy in Multimodal Perception for Robust Reinforcement Learning Agentscited by 6
  34. 2021Adaptation through prediction: multisensory active inference torque controlcited by 6
  35. 2022Factored World Models for Zero-Shot Generalization in Robotic Manipulationcited by 6
  36. 2022Deep Kernel Learning of Dynamical Models from High-Dimensional Noisy Datacited by 6
  37. 2019State Representation Learning from Demonstrationcited by 5
  38. 2021A Versatile and Efficient Reinforcement Learning Framework for Autonomous Drivingcited by 5

50 most cited of 125 All 125 (JSON)