mlsanityData to 7 Oct 2026

Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics

arXiv 1901.08651 ↗First posted 24 Jan 2019cs.LG cs.RO stat.MLcited by 21

Not on the map. Why?

Abstract (arXiv)

Scaling end-to-end reinforcement learning to control real robots from vision presents a series of challenges, in particular in terms of sample efficiency. Against end-to-end learning, state representation learning can help learn a compact, efficient and relevant representation of states that speeds up policy learning, reducing the number of samples needed, and that is easier to interpret. We evaluate several state representation learning methods on goal based robotics tasks and propose a new unsupervised model that stacks representations and combines strengths of several of these approaches. This method encodes all the relevant features, performs on par or better than end-to-end learning with better sample efficiency, and is robust to hyper-parameters change.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 7; 2023: 3; 2024: 2; 2025: 2.

21 papers.

Sort:

By area:

  1. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  2. 2021Acquisition of Chess Knowledge in AlphaZerocited by 120
  3. 2023Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZerocited by 41
  4. 2024Multi-Agent Reinforcement Learning for Autonomous Driving: A Surveycited by 30
  5. 2023Explainable Reinforcement Learning via a Causal World Modelcited by 22
  6. 2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Reviewcited by 18
  7. 2021Continual Learning in Deep Networks: an Analysis of the Last Layercited by 17
  8. 2021Low Dimensional State Representation Learning with Robotics Priors in Continuous Action Spacescited by 9
  9. 2021VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Expertscited by 6
  10. 2021Learning from learning machines: a new generation of AI technology to meet the needs of sciencecited by 3
  11. 2022Using Deep Reinforcement Learning with Automatic Curriculum Learning for Mapless Navigation in Intralogisticscited by 3
  12. 2025Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RLcited by 3
9 more
  1. 2021Scope and Sense of Explainability for AI-Systemscited by 2
  2. 2022End-to-end Reinforcement Learning of Robotic Manipulation with Robust Keypoints Representationcited by 2
  3. 2022Explainable Reinforcement Learning on Financial Stock Trading using SHAPcited by 2
  4. 2022Kinova Gemini: Interactive Robot Grasping with Visual Reasoning and Conversational AIcited by 2
  5. 2023Algebras of actions in an agent's representations of the worldcited by 2
  6. 2022Neural Distillation as a State Representation Bottleneck in Reinforcement Learningcited by 1
  7. 2021POAR: Efficient Policy Optimization via Online Abstract State Representation Learningcited by 0
  8. 2024CIER: A Novel Experience Replay Approach with Causal Inference in Deep Reinforcement Learningcited by 0
  9. 2025Recurrent Auto-Encoders for Enhanced Deep Reinforcement Learning in Wilderness Search and Rescue Planningcited by 0