mlsanityData to 7 Oct 2026

Aligning Robot and Human Representations

arXiv 2302.01928 ↗First posted 3 Feb 2023cs.RO cs.AI cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

To act in the world, robots rely on a representation of salient task aspects: for example, to carry a coffee mug, a robot may consider movement efficiency or mug orientation in its behavior. However, if we want robots to act for and with people, their representations must not be just functional but also reflective of what humans care about, i.e. they must be aligned. We observe that current learning approaches suffer from representation misalignment, where the robot's learned representation does not capture the human's representation. We suggest that because humans are the ultimate evaluator of robot performance, we must explicitly focus our efforts on aligning learned representations with humans, in addition to learning the downstream task. We advocate that current representation learning approaches in robotics should be studied from the perspective of how well they accomplish the objective of representation alignment. We mathematically define the problem, identify its key desiderata, and situate current methods within this formalism. We conclude by suggesting future directions for exploring open challenges.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 84 of its 167 references that are in the map. First posted on arXiv 3 Feb 2023.

Builds on

84 of 167 references.

References · 84

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2017Deep reinforcement learning from human preferencescited by 3,846
  6. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
  7. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  8. 2016Concrete Problems in AI Safetycited by 1,582
  9. 2016Understanding intermediate layers using linear classifier probescited by 1,279
  10. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  11. 2018Recurrent World Models Facilitate Policy Evolutioncited by 761
  12. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
38 more
  1. 2018Diversity is All You Need: Learning Skills without a Reward Functioncited by 734
  2. 2017Spectrally-normalized margin bounds for neural networkscited by 681
  3. 2021CLIPort: What and Where Pathways for Robotic Manipulationcited by 617
  4. 2018Behavioral Cloning from Observationcited by 482
  5. 2018An Algorithmic Perspective on Imitation Learningcited by 455
  6. 2020Learning Invariant Representations for Reinforcement Learning without Reconstructioncited by 424
  7. 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 400
  8. 2022Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videoscited by 338
  9. 2018Reward learning from human preferences and demonstrations in Ataricited by 314
  10. 2019Learning Latent Plans from Playcited by 310
  11. 2021PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-trainingcited by 298
  12. 2017Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperationcited by 286
  13. 2019Causal Confusion in Imitation Learningcited by 286
  14. 2015Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Imagescited by 266
  15. 2015A Review of Relational Machine Learning for Knowledge Graphscited by 264
  16. 2020Decoupling Representation Learning from Reinforcement Learningcited by 263
  17. 2017Inverse Reward Designcited by 246
  18. 2015The Variational Fair Autoencodercited by 223
  19. 2020Few-Shot Learning via Learning the Representation, Provablycited by 213
  20. 2020How Well Do Self-Supervised Models Transfer?cited by 213
  21. 2022Bayesian Structure Learning with Generative Flow Networkscited by 153
  22. 2017DARLA: Improving Zero-Shot Transfer in Reinforcement Learningcited by 147
  23. 2019Unsupervised State Representation Learning in Ataricited by 144
  24. 2017Visualizing and Understanding Atari Agentscited by 141
  25. 2018State Representation Learning for Control: An Overviewcited by 125
  26. 2017Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spacescited by 122
  27. 2019End-to-End Robotic Reinforcement Learning without Reward Engineeringcited by 115
  28. 2021Pretraining Representations for Data-Efficient Reinforcement Learningcited by 105
  29. 2019Reinforcement Knowledge Graph Reasoning for Explainable Recommendationcited by 102
  30. 2017Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstrationcited by 100
  31. 2018Playing hard exploration games by watching YouTubecited by 98
  32. 2021Representation Matters: Offline Pretraining for Sequential Decision Makingcited by 90
  33. 2021Self-Supervised Pretraining Improves Self-Supervised Pretrainingcited by 81
  34. 2020Causal Discovery in Physical Systems from Videoscited by 77
  35. 2020Safe Imitation Learning via Fast Bayesian Reward Inference from Preferencescited by 73
  36. 2021On the Expressivity of Markov Rewardcited by 71
  37. 2021A Survey on Interpretable Reinforcement Learningcited by 70
  38. 2018Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definitioncited by 66

50 most cited of 84 All 84 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 3; 2026: 5.

11 papers.

  1. 2024Beyond Preferences in AI Alignmentcited by 46
  2. 2024Zero-shot Safety Prediction for Autonomous Robots with Foundation World Modelscited by 6
  3. 2025Contrastive Learning from Exploratory Actions: Leveraging Natural Interactions for Preference Elicitationcited by 3
  4. 2025CIVIL: Causal and Intuitive Visual Imitation Learningcited by 3
  5. 2026Embodied Human Simulation for Quantitative Design and Analysis of Interactive Roboticscited by 1
  6. 2026Robots Influencing Humans to Reveal their Goals during Collaboration and Competitioncited by 1
  7. 2024Towards Interpretable Foundation Models of Robot Behavior: A Task Specific Policy Generation Approachcited by 0
  8. 2025Structured Imitation Learning of Interactive Policies through Inverse Gamescited by 0
  9. 2026SMAC: Score-Matched Actor-Critics for Robust Offline-to-Online Transfercited by 0
  10. 2026A Taxonomy of Conceptual Alignment in Human-Robot Dialoguecited by 0
  11. 2026Corrigible Assistance in One Round: Pragmatic-Pedagogic Best Responsecited by 0