# Aligning Robot and Human Representations

arXiv: https://arxiv.org/abs/2302.01928 · HTML: https://mlsanity.com/paper/2302.01928/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 84 of its 167 references that are in the map.
- First posted on arXiv 3 Feb 2023.

## Builds on (most cited first, 30 of 84)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [Diversity is All You Need: Learning Skills without a Reward Function](https://mlsanity.com/paper/1802.06070/) (2018)
- [Spectrally-normalized margin bounds for neural networks](https://mlsanity.com/paper/1706.08498/) (2017)
- [CLIPort: What and Where Pathways for Robotic Manipulation](https://mlsanity.com/paper/2109.12098/) (2021)
- [Behavioral Cloning from Observation](https://mlsanity.com/paper/1805.01954/) (2018)
- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)
- [Learning Invariant Representations for Reinforcement Learning without Reconstruction](https://mlsanity.com/paper/2006.10742/) (2020)
- [Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization](https://mlsanity.com/paper/1603.00448/) (2016)
- [Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos](https://mlsanity.com/paper/2206.11795/) (2022)
- [Reward learning from human preferences and demonstrations in Atari](https://mlsanity.com/paper/1811.06521/) (2018)
- [Learning Latent Plans from Play](https://mlsanity.com/paper/1903.01973/) (2019)
- [PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training](https://mlsanity.com/paper/2106.05091/) (2021)
- [Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation](https://mlsanity.com/paper/1710.04615/) (2017)
- [Causal Confusion in Imitation Learning](https://mlsanity.com/paper/1905.11979/) (2019)
- [Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images](https://mlsanity.com/paper/1506.07365/) (2015)
- [Decoupling Representation Learning from Reinforcement Learning](https://mlsanity.com/paper/2009.08319/) (2020)
- [A Review of Relational Machine Learning for Knowledge Graphs](https://mlsanity.com/paper/1503.00759/) (2015)
- [Inverse Reward Design](https://mlsanity.com/paper/1711.02827/) (2017)
- [The Variational Fair Autoencoder](https://mlsanity.com/paper/1511.00830/) (2015)

## Built on by (most cited first, 11 of 11)

- [Beyond Preferences in AI Alignment](https://mlsanity.com/paper/2408.16984/) (2024)
- [Zero-shot Safety Prediction for Autonomous Robots with Foundation World Models](https://mlsanity.com/paper/2404.00462/) (2024)
- [Contrastive Learning from Exploratory Actions: Leveraging Natural Interactions for Preference Elicitation](https://mlsanity.com/paper/2501.01367/) (2025)
- [CIVIL: Causal and Intuitive Visual Imitation Learning](https://mlsanity.com/paper/2504.17959/) (2025)
- [Embodied Human Simulation for Quantitative Design and Analysis of Interactive Robotics](https://mlsanity.com/paper/2603.09218/) (2026)
- [Robots Influencing Humans to Reveal their Goals during Collaboration and Competition](https://mlsanity.com/paper/2609.05519/) (2026)
- [Towards Interpretable Foundation Models of Robot Behavior: A Task Specific Policy Generation Approach](https://mlsanity.com/paper/2407.08065/) (2024)
- [Structured Imitation Learning of Interactive Policies through Inverse Games](https://mlsanity.com/paper/2511.12848/) (2025)
- [SMAC: Score-Matched Actor-Critics for Robust Offline-to-Online Transfer](https://mlsanity.com/paper/2602.17632/) (2026)
- [A Taxonomy of Conceptual Alignment in Human-Robot Dialogue](https://mlsanity.com/paper/2606.22360/) (2026)
- [Corrigible Assistance in One Round: Pragmatic-Pedagogic Best Response](https://mlsanity.com/paper/2607.27508/) (2026)

## 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.