mlsanityData to 14 Oct 2026

Deep Interpretable Models of Theory of Mind

arXiv 2104.02938 ↗First posted 7 Apr 2021cs.LG cs.AIcited by 13

Not on the map. Why?

Abstract (arXiv)

When developing AI systems that interact with humans, it is essential to design both a system that can understand humans, and a system that humans can understand. Most deep network based agent-modeling approaches are 1) not interpretable and 2) only model external behavior, ignoring internal mental states, which potentially limits their capability for assistance, interventions, discovering false beliefs, etc. To this end, we develop an interpretable modular neural framework for modeling the intentions of other observed entities. We demonstrate the efficacy of our approach with experiments on data from human participants on a search and rescue task in Minecraft, and show that incorporating interpretability can significantly increase predictive performance under the right conditions.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 22 of its 39 references that are in the map. First posted on arXiv 7 Apr 2021.

Builds on

22 of 39 references.

References · 22

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  5. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  6. 2016Generative Adversarial Imitation Learningcited by 1,597
  7. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  8. 2018Sanity Checks for Saliency Mapscited by 1,156
  9. 2017SmoothGrad: removing noise by adding noisecited by 1,109
  10. 2020Concept Bottleneck Modelscited by 1,032
  11. 2018Behavioral Cloning from Observationcited by 492
  12. 2018Machine Theory of Mindcited by 226
10 more
  1. 2020Concept Whitening for Interpretable Image Recognitioncited by 225
  2. 2017Learning with Opponent-Learning Awarenesscited by 222
  3. 2018Programmatically Interpretable Reinforcement Learningcited by 193
  4. 2019Iterative Normalization: Beyond Standardization towards Efficient Whiteningcited by 92
  5. 2019Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learningcited by 68
  6. 2019On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inferencecited by 49
  7. 2018Transparency and Explanation in Deep Reinforcement Learning Neural Networkscited by 40
  8. 2018Towards Better Interpretability in Deep Q-Networkscited by 22
  9. 2019On the Utility of Model Learning in HRIcited by 21
  10. 2020StylePredict: Machine Theory of Mind for Human Driver Behavior From Trajectoriescited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 3; 2024: 2; 2025: 2; 2026: 2.

13 papers.

Sort:

By area:

  1. 2023Theory of Mind as Intrinsic Motivation for Multi-Agent Reinforcement Learningcited by 19
  2. 2024Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communicationcited by 17
  3. 2025MOMENTS: A Comprehensive Multimodal Benchmark for Theory of Mindcited by 13
  4. 2024Limits of Theory of Mind Modelling in Dialogue-Based Collaborative Plan Acquisitioncited by 10
  5. 2022Learning Theory of Mind via Dynamic Traits Attributioncited by 5
  6. 2022Modeling Human-AI Team Decision Makingcited by 2
  7. 2022Robot Learning Theory of Mind through Self-Observation: Exploiting the Intentions-Beliefs Synergycited by 2
  8. 2022Modeling Human Behavior Part I -- Learning and Belief Approachescited by 1
  9. 2025Integrating Machine Learning into Belief-Desire-Intention Agents: Current Advances and Open Challengescited by 1
  10. 2026A formal definition and meta-model for a machine theory of mindcited by 1
  11. 2023Probabilistic Modeling of Human Teams to Infer False Beliefscited by 0
  12. 2023Personalized Decision Supports based on Theory of Mind Modeling and Explainable Reinforcement Learningcited by 0
1 more
  1. 2026A Causal Model of Theory of Mind in Conflict for Artificial Intelligencecited by 0