mlsanityData to 14 Oct 2026

MIRROR: Differentiable Deep Social Projection for Assistive Human-Robot Communication

arXiv 2203.02877 ↗First posted 6 Mar 2022cs.AI cs.HC cs.LGcited by 7

On the map: Offline RL and imitation learning from data → Robot manipulation imitation learning

Abstract (arXiv)

Communication is a hallmark of intelligence. In this work, we present MIRROR, an approach to (i) quickly learn human models from human demonstrations, and (ii) use the models for subsequent communication planning in assistive shared-control settings. MIRROR is inspired by social projection theory, which hypothesizes that humans use self-models to understand others. Likewise, MIRROR leverages self-models learned using reinforcement learning to bootstrap human modeling. Experiments with simulated humans show that this approach leads to rapid learning and more robust models compared to existing behavioral cloning and state-of-the-art imitation learning methods. We also present a human-subject study using the CARLA simulator which shows that (i) MIRROR is able to scale to complex domains with high-dimensional observations and complicated world physics and (ii) provides effective assistive communication that enabled participants to drive more safely in adverse weather conditions.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 27 of its 53 references that are in the map. First posted on arXiv 6 Mar 2022.

Builds on

27 of 53 references.

References · 27

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  3. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  4. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  5. 2016Generative Adversarial Imitation Learningcited by 1,597
  6. 2020Reinforcement Learning with Augmented Datacited by 468
  7. 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 349
  8. 2019Vision-and-Dialog Navigationcited by 250
  9. 2019Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Modelcited by 231
  10. 2018Multimodal Generative Models for Scalable Weakly-Supervised Learningcited by 200
  11. 2018Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Taskscited by 154
  12. 2016Modeling Missing Data in Clinical Time Series with RNNscited by 80
15 more
  1. 2018Where Do You Think You're Going?: Inferring Beliefs about Dynamics from Behaviorcited by 40
  2. 2020When Humans Aren't Optimal: Robots that Collaborate with Risk-Aware Humanscited by 34
  3. 2021Explainable AI for Robot Failures: Generating Explanations that Improve User Assistance in Fault Recoverycited by 32
  4. 2020Residual Policy Learning for Shared Autonomycited by 26
  5. 2021Cognitive science as a source of forward and inverse models of human decisions for robotics and controlcited by 22
  6. 2019On the Utility of Model Learning in HRIcited by 21
  7. 2014A Review of Verbal and Non-Verbal Human-Robot Interactive Communicationcited by 16
  8. 2020Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimizationcited by 16
  9. 2018Personalized Dynamics Models for Adaptive Assistive Navigation Systemscited by 13
  10. 2021Multi-Modal Mutual Information (MuMMI) Training for Robust Self-Supervised Deep Reinforcement Learningcited by 13
  11. 2018Multi-Task Trust Transfer for Human-Robot Interactioncited by 11
  12. 2019Factorized Inference in Deep Markov Models for Incomplete Multimodal Time Seriescited by 10
  13. 2020Assisted Perception: Optimizing Observations to Communicate Statecited by 10
  14. 2020Getting to Know One Another: Calibrating Intent, Capabilities and Trust for Human-Robot Collaborationcited by 7
  15. 2019Robot Capability and Intention in Trust-based Decisions across Taskscited by 6

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 4; 2024: 0; 2025: 2.

7 papers.

  1. 2023Translating Natural Language to Planning Goals with Large-Language Modelscited by 133
  2. 2023Large Language Models as Zero-Shot Human Models for Human-Robot Interactioncited by 30
  3. 2023Graph-enabled Reinforcement Learning for Time Series Forecasting with Adaptive Intelligencecited by 5
  4. 2025Shared Autonomy for Proximal Teachingcited by 4
  5. 2022Modeling Mobile Health Users as Reinforcement Learning Agentscited by 2
  6. 2023Latent Emission-Augmented Perspective-Taking (LEAPT) for Human-Robot Interactioncited by 0
  7. 2025Performance Asymmetry in Model-Based Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Mirror Learning
  2. 2025Social Human Robot Embodied Conversation (SHREC) Dataset: Benchmarking Foundational Models' Social Reasoning
  3. 2024Enhancing Robot Assistive Behaviour with Reinforcement Learning and Theory of Mind
  4. 2026Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning
  5. 2026GazeVLA: Learning Human Intention for Robotic Manipulation
  6. 2019Imitating by generating: deep generative models for imitation of interactive tasks
  7. 2021Learning to Share Autonomy Across Repeated Interaction
  8. 2024Learning to Assist Humans without Inferring Rewards