mlsanityData to 14 Oct 2026

Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning

arXiv 1703.02949 ↗First posted 8 Mar 2017cs.AI cs.ROcited by 85

Not on the map. Why?

Cited by 23 in Offline RL and imitation learning from data, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

People can learn a wide range of tasks from their own experience, but can also learn from observing other creatures. This can accelerate acquisition of new skills even when the observed agent differs substantially from the learning agent in terms of morphology. In this paper, we examine how reinforcement learning algorithms can transfer knowledge between morphologically different agents (e.g., different robots). We introduce a problem formulation where two agents are tasked with learning multiple skills by sharing information. Our method uses the skills that were learned by both agents to train invariant feature spaces that can then be used to transfer other skills from one agent to another. The process of learning these invariant feature spaces can be viewed as a kind of "analogy making", or implicit learning of partial correspondences between two distinct domains. We evaluate our transfer learning algorithm in two simulated robotic manipulation skills, and illustrate that we can transfer knowledge between simulated robotic arms with different numbers of links, as well as simulated arms with different actuation mechanisms, where one robot is torque-driven while the other is tendon-driven.

Key facts. Cited by 85 papers in the map (data through 14 Oct 2026). First posted on arXiv 8 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 2; 2019: 3; 2020: 3; 2021: 20; 2022: 20; 2023: 12; 2024: 14; 2025: 7; 2026: 4.

85 papers.

Sort:

By area:

  1. 2018Behavioral Cloning from Observationcited by 492
  2. 2018An Algorithmic Perspective on Imitation Learningcited by 459
  3. 2022GNM: A General Navigation Model to Drive Any Robotcited by 171
  4. 2021Rapid Exploration for Open-World Navigation with Latent Goal Modelscited by 121
  5. 2021XIRL: Cross-embodiment Inverse Reinforcement Learningcited by 107
  6. 2019Recent Advances in Imitation Learning from Observationcited by 93
  7. 2022MyoSuite -- A contact-rich simulation suite for musculoskeletal motor controlcited by 80
  8. 2021Cross-Domain Imitation Learning via Optimal Transportcited by 49
  9. 2022GenLoco: Generalized Locomotion Controllers for Quadrupedal Robotscited by 48
  10. 2022Graph Inverse Reinforcement Learning from Diverse Videoscited by 46
  11. 2021Cross-domain Imitation from Observationscited by 42
  12. 2021UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformerscited by 39
38 more
  1. 2023Multi-agent Reinforcement Learning: A Comprehensive Surveycited by 33
  2. 2021Unsupervised Visual Attention and Invariance for Reinforcement Learningcited by 30
  3. 2022Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objectivecited by 28
  4. 2022Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectoriescited by 28
  5. 2023Polybot: Training One Policy Across Robots While Embracing Variabilitycited by 28
  6. 2021Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoningcited by 26
  7. 2023Markerless Camera-to-Robot Pose Estimation via Self-supervised Sim-to-Real Transfercited by 24
  8. 2019Imitation Learning from Video by Leveraging Proprioceptioncited by 23
  9. 2021Domain-Robust Visual Imitation Learning with Mutual Information Constraintscited by 20
  10. 2021Transfer Learning for Future Wireless Networks: A Comprehensive Surveycited by 18
  11. 2022Transfer RL across Observation Feature Spaces via Model-Based Regularizationcited by 18
  12. 2024Cross-Embodiment Robot Manipulation Skill Transfer using Latent Space Alignmentcited by 18
  13. 2023Structure in Deep Reinforcement Learning: A Survey and Open Problemscited by 16
  14. 2024A Comprehensive Survey of Cross-Domain Policy Transfer for Embodied Agentscited by 16
  15. 2022Learn what matters: cross-domain imitation learning with task-relevant embeddingscited by 14
  16. 2021Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Taskscited by 13
  17. 2021A New Representation of Successor Features for Transfer across Dissimilar Environmentscited by 13
  18. 2021Policy Transfer across Visual and Dynamics Domain Gaps via Iterative Groundingcited by 12
  19. 2022Imitation Learning from Observations under Transition Model Disparitycited by 11
  20. 2021Linear Representation Meta-Reinforcement Learning for Instant Adaptationcited by 9
  21. 2024xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editingcited by 9
  22. 2021Cross Domain Robot Imitation with Invariant Representationcited by 8
  23. 2022Weakly Supervised Correspondence Learningcited by 7
  24. 2019Domain Adaptive Imitation Learningcited by 6
  25. 2021Semantic-Aware Collaborative Deep Reinforcement Learning Over Wireless Cellular Networkscited by 6
  26. 2026Flow Actor-Critic for Offline Reinforcement Learningcited by 6
  27. 2021Skeletal Feature Compensation for Imitation Learning with Embodiment Mismatchcited by 5
  28. 2022Learning from Imperfect Demonstrations via Adversarial Confidence Transfercited by 5
  29. 2022Learning Action Translator for Meta Reinforcement Learning on Sparse-Reward Taskscited by 5
  30. 2022RMBench: Benchmarking Deep Reinforcement Learning for Robotic Manipulator Controlcited by 5
  31. 2024Cross Domain Policy Transfer with Effect Cycle-Consistencycited by 5
  32. 2025IL-SOAR : Imitation Learning with Soft Optimistic Actor cRiticcited by 5
  33. 2021Pattern Transfer Learning for Reinforcement Learning in Order Dispatchingcited by 4
  34. 2023Similarity-based Knowledge Transfer for Cross-Domain Reinforcement Learningcited by 4
  35. 2024Task and Domain Adaptive Reinforcement Learning for Robot Controlcited by 4
  36. 2024Simulation-Aided Policy Tuning for Black-Box Robot Learningcited by 4
  37. 2025Invariance Co-training for Robot Visual Generalizationcited by 4
  38. 2024Zero-shot cross-modal transfer of Reinforcement Learning policies through a Global Workspacecited by 3

50 most cited of 85 All 85 (JSON)