# Robot Learning Theory of Mind through Self-Observation: Exploiting the Intentions-Beliefs Synergy

arXiv: https://arxiv.org/abs/2210.09435 · HTML: https://mlsanity.com/paper/2210.09435/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 63 references that are in the map.
- First posted on arXiv 17 Oct 2022.

## Builds on (most cited first, 17 of 17)

- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [Object Goal Navigation using Goal-Oriented Semantic Exploration](https://mlsanity.com/paper/2007.00643/) (2020)
- [Multi-Task Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2009.09796/) (2020)
- [Machine Theory of Mind](https://mlsanity.com/paper/1802.07740/) (2018)
- [The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines](https://mlsanity.com/paper/2005.00343/) (2020)
- [Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1901.09207/) (2019)
- [A Dataset for Developing and Benchmarking Active Vision](https://mlsanity.com/paper/1702.08272/) (2017)
- [On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference](https://mlsanity.com/paper/1906.09624/) (2019)
- [Mind the gap: Challenges of deep learning approaches to Theory of Mind](https://mlsanity.com/paper/2203.16540/) (2022)
- [Emergence of Exploratory Look-Around Behaviors through Active Observation Completion](https://mlsanity.com/paper/1906.11407/) (2019)
- [Deep Interpretable Models of Theory of Mind](https://mlsanity.com/paper/2104.02938/) (2021)
- [StylePredict: Machine Theory of Mind for Human Driver Behavior From Trajectories](https://mlsanity.com/paper/2011.04816/) (2020)
- [Interactive AI with a Theory of Mind](https://mlsanity.com/paper/1912.05284/) (2019)
- [Learning Theory of Mind via Dynamic Traits Attribution](https://mlsanity.com/paper/2204.09047/) (2022)
- [Proactive Intention Recognition for Joint Human-Robot Search and Rescue Missions through Monte-Carlo Planning in POMDP Environments](https://mlsanity.com/paper/1908.10125/) (2019)
- [Functional advantages of an adaptive Theory of Mind for robotics: a review of current architectures](https://mlsanity.com/paper/1909.00193/) (2019)
- [Transferring Adaptive Theory of Mind to social robots: insights from developmental psychology to robotics](https://mlsanity.com/paper/1909.00197/) (2019)

## Built on by (most cited first, 2 of 2)

- [World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges](https://mlsanity.com/paper/2301.05832/) (2023)
- [Who Sees What? Structured Thought-Action Sequences for Epistemic Reasoning in LLMs](https://mlsanity.com/paper/2508.14564/) (2025)

## Abstract (arXiv)

In complex environments, where the human sensory system reaches its limits, our behaviour is strongly driven by our beliefs about the state of the world around us. Accessing others' beliefs, intentions, or mental states in general, could thus allow for more effective social interactions in natural contexts. Yet these variables are not directly observable. Theory of Mind (TOM), the ability to attribute to other agents' beliefs, intentions, or mental states in general, is a crucial feature of human social interaction and has become of interest to the robotics community. Recently, new models that are able to learn TOM have been introduced. In this paper, we show the synergy between learning to predict low-level mental states, such as intentions and goals, and attributing high-level ones, such as beliefs. Assuming that learning of beliefs can take place by observing own decision and beliefs estimation processes in partially observable environments and using a simple feed-forward deep learning model, we show that when learning to predict others' intentions and actions, faster and more accurate predictions can be acquired if beliefs attribution is learnt simultaneously with action and intentions prediction. We show that the learning performance improves even when observing agents with a different decision process and is higher when observing beliefs-driven chunks of behaviour. We propose that our architectural approach can be relevant for the design of future adaptive social robots that should be able to autonomously understand and assist human partners in novel natural environments and tasks.